Monday July 12, 2010 |
07:00–08:45
|
Venue A, Foyer
Registration
|
08:45–09:00
|
Venue A, Aula
Opening
|
09:00–10:00
|
Invited Talk by Zenzi M Griffin, Towards a Psycholinguistics of Social Interaction
Chair: Sandra Carberry
show abstracthide abstractIn studying spoken language production and comprehension, psycholinguistic researchers have typically designed experiments in which content consists of decontextualized utterances, narratives, or descriptions of visual displays (even when studying naïve participants in dialog). Like the drunk in the night who looks for keys where the light is brightest rather than where they were lost, we have studied language processing under the easiest circumstances to manipulate and control rather than study the speech acts and discourse functions that language use more often involves. I will argue that we now have resources available to extend experimental research to language use that has little or nothing to do with description. That is, psycholinguistics is ready to address language processing in interpersonal interactions. I will describe the results of a questionnaire study of parental name substitutions that led to this line of thought.
show biographyhide biographyZenzi Griffin studied psychology at Stockholm University for one year before transferring to Michigan State University, where she completed a BA in Psychology. In 1998, she earned a Ph.D. in Cognitive Psychology (with a minor in Linguistics) from the Department of Psychology at the University of Illinois at Urbana-Champaign. There she worked with Dr. Kathryn Bock and Dr. Gary Dell, becoming one of the first researchers to monitor eye movements to study language production. Dr. Griffin then spent three years as an assistant professor in the Department of Psychology at Stanford University before moving to the School of Psychology at Georgia Tech in the summer of 2001. In 2008, she joined the Department of Psychology at the University of Texas at Austin as a full professor. She is a member of the Editorial Boards of Psychological Review and the Journal of Memory and Language. In addition to a wide range of collaborative projects, Dr. Griffin is currently studying the retrieval and use of personal names.
|
10:00–10:30
|
Venue A, Foyer
Coffee/Tea Break
|
|
Venue A, Aula
|
Venue A, X
|
Venue A, IX
|
Venue B, 3
|
Venue B, 4
|
10:30–11:45
|
|
|
|
|
|
11:45–11:55
|
Short Break
|
11:55–13:15
|
|
|
|
|
|
13:15–15:00
|
|
15:00–16:15
|
|
|
|
|
|
16:15–16:45
|
Venue A and B, Foyer
Coffee/Tea Break
|
16:45–18:00
|
|
|
|
|
|
Tuesday July 13, 2010 |
07:30–09:00
|
Venue A, Foyer
Registration
|
09:00–10:00
|
Venue A, Aula
Lifetime Achievement Award
Chair: Ido Dagan
|
10:00–10:30
|
Venue A, Foyer
Coffee/Tea Break
|
|
Venue A, Aula
|
Venue A, X
|
Venue A, IX
|
Venue B, 3
|
Venue B, 4
|
This cell intentionally left blank |
10:30–11:45
|
|
|
|
|
|
11:45–11:55
|
Short Break
|
11:55–13:15
|
|
|
|
|
|
|
13:15–15:00
|
|
15:00–16:15
|
|
|
|
|
|
|
16:15–16:45
|
Venue A and B, Foyer
Coffee/Tea Break
|
16:45–17:35
|
|
|
|
|
|
Wednesday July 14, 2010 |
07:30–09:00
|
Venue A, Foyer
Registration
|
09:00–10:00
|
Venue A, Aula
Invited Talk by Andrei Broder, Computational Advertising
Chair: Stephen Clark
show abstracthide abstractComputational advertising is an emerging new scientific sub-discipline, at the intersection of large scale search and text analysis, information retrieval, statistical modeling, machine learning, classification, optimization, and microeconomics. The central challenge of computational advertising is to find the "best match" between a given user in a given context and a suitable advertisement. The context could be a user entering a query in a search engine ("sponsored search") , a user reading a web page ("content match" and "display ads"), a user watching a movie on a portable device, and so on. The information about the user can vary from scarily detailed to practically nil. The number of potential advertisements might be in the billions. Thus, depending on the definition of "best match" this challenge leads to a variety of massive optimization and search problems, with complicated constraints. This talk will give an introduction to this area focusing on the interplay between science, engineering, and marketplace.
show biographyhide biographyAndrei Broder is a Yahoo! Fellow and Vice President for Computational Advertising. He also serves as Chief Scientist for Yahoo’s Search and Advertising Product Groups. Previously he was an IBM Distinguished Engineer and the CTO of the Institute for Search and Text Analysis in IBM Research. From 1999 until 2002 he was Vice President for Research and Chief Scientist at the AltaVista Company. He was graduated Summa cum Laude from Technion, the Israeli Institute of Technology, and obtained his M.Sc. and Ph.D. in Computer Science at Stanford University under Don Knuth. His current research interests are centered on computational advertising, web search, context-driven information supply, and randomized algorithms. Broder is co-winner of the Best Paper award at WWW6 (for his work on near-duplicate page detection) and at WWW9 (for his work on mapping the web). He has authored more than a hundred papers and was awarded twenty-five patents. He is a member of the US National Academy of Engineering, a fellow of ACM and of IEEE, and past chair of the IEEE Technical Committee on Mathematical Foundations of Computing.
|
10:00–10:30
|
Venue A, Foyer
Coffee/Tea Break
|
|
Venue A, Aula
|
Venue A, X
|
Venue A, IX
|
Venue B, 3
|
Venue B, 4
|
10:30–12:10
|
|
|
|
|
|
12:10–12:20
|
Short Break
|
12:20–13:20 |
Venue A, Aula
ACL Business Meeting
|
13:00–14:30
|
Venue A, Foyer
Lunch (Complimentary)
|
14:30–15:45
|
|
|
|
|
|
15:45–16:15
|
Venue A and B, Foyer
Coffee/Tea Break
|
16:15–17:30
|
|
|
|
|
|
17:30–17:40
|
Short Break
|
17:40–18:15
|
|
|
01 |
Pseudo-Word for Phrase-Based Machine Translation
Xiangyu Duan, Min Zhang and Haizhou Li
show abstracthide abstractThe pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained in some cases such as non-compositional phrasal equivalences, where no clear word alignments exist. Using words as inputs to PB-SMT pipeline has inborn deficiency. This paper proposes pseudo-word as a new start point for PB-SMT pipeline. Pseudo-word is a kind of basic multi-word expression that characterizes minimal sequence of consecutive words in sense of translation. By casting pseudo-word searching problem into a parsing framework, we search for pseudo-words in a monolingual way and a bilingual synchronous way. Experiments show that pseudo-word significantly outperforms word for PB-SMT model in both travel translation domain and news translation domain.
|
02 |
Hierarchical Search for Word Alignment
Jason Riesa and Daniel Marcu
show abstracthide abstractWe present a simple yet powerful hierarchical search algorithm for automatic word alignment. Our algorithm induces a forest of alignments from which we can efficiently extract a ranked k-best list. We score a given alignment within the forest with a flexible, linear discriminative model incorporating hundreds of features, and trained on a relatively small amount of annotated data. We report results on Arabic-English word alignment and translation tasks. Our model outperforms a GIZA++ Model-4 baseline by 6.3 points in F-measure, yielding a 1.1 BLEU score increase over a state-of-the-art syntax-based machine translation system.
|
03 |
Paraphrase Lattice for Statistical Machine Translation
Takashi Onishi, Masao Utiyama and Eiichiro Sumita
show abstracthide abstractLattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. We show that lattice decoding is also useful for handling input variations. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to the lattice decoder. The decoder selects the best path for decoding. Using these paraphrase lattices as inputs, we obtained significant gains in BLEU scores for IWSLT and Europarl datasets.
|
04 |
A Joint Rule Selection Model for Hierarchical Phrase-Based Translation
Lei Cui, Dongdong Zhang, Mu Li, Ming Zhou and Tiejun Zhao
show abstracthide abstractIn hierarchical phrase-based SMT systems, statistical models are integrated to guide the hierarchical rule selection for better translation performance. Previous work mainly focused on the selection of either the source side of a hierarchical rule or the target side of a hierarchical rule rather than considering both of them simultaneously. This paper presents a joint model to predict the selection of hierarchical rules. The proposed model is estimated based on four sub-models where the rich context knowledge from both source and target sides is leveraged. Our method can be easily incorporated into the practical SMT systems with the log-linear model framework. The experimental results show that our method can yield significant improvements in performance.
|
05 |
Learning Lexicalized Reordering Models from Reordering Graphs
Jinsong Su, Yang Liu, Yajuan Lv, Haitao Mi and Qun Liu
show abstracthide abstractLexicalized reordering models play a crucial role in phrase-based translation systems. They are usually learned from the word-aligned bilingual corpus by examining the reordering relations of adjacent phrases. Instead of just checking whether there is one phrase adjacent to a given phrase, we argue that it is important to take the number of adjacent phrases into account for better estimations of reordering models. We propose to use a structure named reordering graph, which represents all phrase segmentations of a sentence pair, to learn lexicalized reordering models efficiently. Experimental results on the NIST Chinese-English test sets show that our approach significantly outperforms the baseline method.
|
06 |
Filtering Syntactic Constraints for Statistical Machine Translation
Hailong Cao and Eiichiro Sumita
show abstracthide abstractSource language parse trees offer very useful but imperfect reordering constraints for statistical machine translation. A lot of effort has been made for soft applications of syntactic constraints. We alternatively propose the selective use of syntactic constraints. A classifier is built automatically to decide whether a node in the parse trees should be used as a reordering constraint or not. Using this information yields a 0.8 BLEU point improvement over a full constraint-based system.
|
07 |
Diversify and Combine: Improving Word Alignment for Machine Translation on Low-Resource Languages
Bing Xiang, Yonggang Deng and Bowen Zhou
show abstracthide abstractWe present a novel method to improve word alignment quality and eventually the translation performance by producing and combining complementary word alignments for low-resource languages. Instead of focusing on the improvement of a single set of word alignments, we generate multiple sets of diversified alignments based on different motivations, such as linguistic knowledge, morphology and heuristics. We demonstrate this approach on an English-to-Pashto translation task by combining the alignments obtained from syntactic reordering, stemming, and partial words. The combined alignment outperforms the baseline alignment, with significantly higher F-scores and better translation performance.
|
08 |
Efficient Path Counting Transducers for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices
Graeme Blackwood, Adrià de Gispert and William Byrne
show abstracthide abstractThis paper presents an efficient implementation of linearized lattice minimum Bayes-risk decoding using weighted finite state transducers. We introduce transducers to efficiently count lattice paths containing n-grams and use these to gather the required statistics. We show that these procedures can be implemented exactly through simple transformations of word sequences to sequences of n-grams. This yields a novel implementation of lattice minimum Bayes-risk decoding which is fast and exact even for very large lattices.
|
09 |
Word Alignment with Synonym Regularization
Hiroyuki Shindo, Akinori Fujino and Masaaki Nagata
show abstracthide abstractWe present a novel framework for word alignment that incorporates synonym knowledge collected from monolingual linguistic resources in a bilingual probabilistic model. Synonym information is helpful for word alignment because we can expect a synonym to correspond to the same word in a different language. We design a generative model for word alignment that uses synonym information as a regularization term. The experimental results show that our proposed method significantly improves word alignment quality.
|
10 |
Better Filtration and Augmentation for Hierarchical Phrase-Based Translation Rules
Zhiyang Wang, Yajuan Lv, Qun Liu and Young-Sook Hwang
show abstracthide abstractThis paper presents a novel filtration criterion to restrict the rule extraction for the hierarchical phrase-based translation model, where a bilingual but relaxed well-formed dependency restriction is used to filter out bad rules. Furthermore, a new feature which describes the regularity that the source/target dependency edge triggers the target/source word is also proposed. Experimental results show that, the new criteria weeds out about 40\% rules while with translation performance improvement, and the new feature brings another improvement to the baseline system, especially on larger corpus.
|
11 |
Fixed Length Word Suffix for Factored Statistical Machine Translation
Narges Sharif Razavian and Stephan Vogel
show abstracthide abstractFactored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, including the Part of Speech tags in improving the grammaticality of the output. However, high quality part of speech taggers are not available in open domain for many languages. In this paper we used fixed length word suffix as a new factor in the Factored SMT to replace the part of speech tag factors, and were able to achieve significant improvements in three set of experiments: large NIST Arabic to English system, medium WMT Spanish to English system, and small TRANSTAC English to Iraqi system.
|
|
13 |
The Prevalence of Descriptive Referring Expressions in News and Narrative
Raquel Hervas and Mark Finlayson
show abstracthide abstractGenerating referring expressions is a key step in Natural Language Generation. Researchers have focused almost exclusively on generating distinctive referring expressions, that is, referring expressions that uniquely identify their intended referent. While undoubtedly one of their most important functions, referring expressions can be more than distinctive. In particular, descriptive referring expressions - those that provide additional information not required for distinction - are critical to fluent, efficient, well-written text. We present a corpus analysis in which approximately one-fifth of 7,207 referring expressions in 24,422 words of news and narrative are descriptive. These data show that if we are ever to fully master natural language generation, especially for the genres of news and narrative, researchers will need to devote more attention to understanding how to generate descriptive, and not just distinctive, referring expressions.
|
14 |
Preferences versus Adaptation during Referring Expression Generation
Martijn Goudbeek and Emiel Krahmer
show abstracthide abstractCurrent Referring Expression Generation algorithms rely on domain dependent preferences for both content selection and linguistic realization. We present two experiments showing that human speakers may opt for dispreferred properties and dispreferred modifier orderings when these were salient in a preceding interaction (without speakers being consciously aware of this). We discuss the impact of these findings for current generation algorithms.
|
15 |
Entity-Based Local Coherence Modelling Using Topological Fields
Jackie Chi Kit Cheung and Gerald Penn
show abstracthide abstractOne goal of natural language generation is to produce coherent text that presents information in a logical order. In this paper, we show that topological fields, which model high-level clausal structure, are an important component of local coherence in German. First, we show in a sentence ordering experiment that topological field information improves the entity grid model of Barzilay and Lapata (2008) more than grammatical role and simple clausal order information do, particularly when manual annotations of this information are not available. Then, we incorporate the model enhanced with topological fields into a natural language generation system that generates constituent orders for German text, and show that the added coherence component improves performance slightly, though not statistically significantly.
|
Information Retrieval and Extraction
|
16 |
Recommendation in Internet Forums and Blogs
Jia Wang, Qing Li, Yuanzhu Peter Chen and Zhangxi Lin
show abstracthide abstractThe variety of engaging interactions among users in social medial distinguishes it from traditional Web media. Such a feature should be utilized while attempting to provide intelligent services to social media participants. In this article, we present a framework to recommend relevant information in Internet forums and blogs using user comments, one of the most representative of user behaviors in online discussion. When incorporating user comments, we consider structural, semantic, and authority information carried by them. One of the most important observation from this work is that semantic contents of user comments can play a fairly different role in a different form of social media. When designing a recommendation system for this purpose, such a difference must be considered with caution.
|
17 |
Event-Based Hyperspace Analogue to Language for Query Expansion
Tingxu Yan, Tamsin Maxwell, Dawei Song, Yuexian Hou and Peng Zhang
show abstracthide abstractBag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and validated semantic space model that captures statistical dependencies between words by considering their co-occurrences in a surrounding window of text. HAL has been successfully applied to query expansion in IR, but has several limitations, including high processing cost and use of distributional statistics that do not exploit syntax. In this paper, we pursue two methods for incorporating syntactic-semantic information from textual ’events’ into HAL. We build the HAL space directly from events to investigate whether processing costs can be reduced through more careful definition of word co-occurrence, and improve the quality of the pseudo-relevance feedback by applying event information as a constraint during HAL construction. Both methods significantly improve performance results in comparison with original HAL, and interpolation of HAL and relevance model expansion outperforms either method alone.
|
18 |
Learning Phrase-Based Spelling Error Models from Clickthrough Data
Xu Sun, Jianfeng Gao, Daniel Micol and Chris Quirk
show abstracthide abstractThis paper explores the use of clickthrough data for query spelling correction. First, large amounts of query-correction pairs are derived by analyzing users’ query reformulation behavior encoded in the clickthrough data. Then, a phrase-based error model that accounts for the transformation probability between multi-term phrases is trained and integrated into a query speller system. Ex-periments are carried out on a human-labeled data set. Results show that the system using the phrase-based error model outperforms signifi-cantly its baseline systems.
|
19 |
Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing
Ruihong Huang and Ellen Riloff
show abstracthide abstractThis research explores the idea of inducing domain-specific semantic class taggers using only a domain-specific text collection and seed words. The learning process begins by inducing a classifier that only has access to contextual features, forcing it to generalize beyond the seeds. The contextual classifier then labels new instances, to expand and diversify the training set. Next, a cross-category bootstrapping process simultaneously trains a suite of classifiers for multiple semantic classes. The positive instances for one class are used as negative instances for the others in an iterative bootstrapping cycle. We also explore a one-semantic-class-per-discourse heuristic, and use the classifiers to dynamically create semantic features. We evaluate our approach by inducing six semantic taggers from a collection of veterinary medicine message board posts.
|
20 |
Learning 5000 Relational Extractors
Raphael Hoffmann, Congle Zhang and Daniel S. Weld
show abstracthide abstractMany researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents WPE, a self-supervised, relation-specific IE system which learns 5025 relations - more than an order of magnitude greater than any previous approach - with an average F1 score of 61%. Crucial to WPE’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse.
|
|
21 |
“Was It Good? It Was Provocative.” Learning the Meaning of Scalar Adjectives
Marie-Catherine de Marneffe, Christopher D. Manning and Christopher Potts
show abstracthide abstractTexts and dialogues often express information indirectly. For instance, speakers’ answers to yes/no questions do not always straightforwardly convey a ’yes’ or ’no’ answer. The intended reply is clear in some cases (Was it good? It was great!) but uncertain in others (Was it acceptable? It was unprecedented.). In this paper, we present methods for interpreting the answers to questions like these which involve scalar modifiers. We show how to ground scalar modifier meaning based on data collected from the Web. We learn scales between modifiers and infer the extent to which a given answer conveys ’yes’ or ’no’. To evaluate the methods, we collected examples of question-answer pairs involving scalar modifiers from CNN transcripts and the Dialog Act corpus and use response distributions from Mechanical Turk workers to assess the degree to which each answer conveys ’yes’ or ’no’. Our experimental results closely match the Turkers’ response data, demonstrating that meanings can be learned from Web data and that such meanings can drive pragmatic inference.
|
22 |
The Same-Head Heuristic for Coreference
Micha Elsner and Eugene Charniak
show abstracthide abstractWe investigate coreference relationships between NPs with the same head noun. It is relatively common in unsupervised work to assume that such pairs are coreferent– but this is not always true, especially if realistic mention detection is used. We describe the distribution of non-coreferent same-head pairs in news text, and present an unsupervised generative model which learns not to link some same-head NPs using syntactic features, improving precision.
|
23 |
Authorship Attribution Using Probabilistic Context-Free Grammars
Sindhu Raghavan, Adriana Kovashka and Raymond Mooney
show abstracthide abstractIn this paper, we present a novel approach for authorship attribution, the task of identifying the author of a document, using probabilistic context-free grammars. Our approach involves building a probabilistic context-free grammar for each author and using this grammar as a language model for classification. We evaluate the performance of our method on a wide range of datasets to demonstrate its efficacy.
|
24 |
The Impact of Interpretation Problems on Tutorial Dialogue
Myroslava O. Dzikovska, Johanna D. Moore, Natalie Steinhauser and Gwendolyn Campbell
show abstracthide abstractSupporting natural language input may improve learning in intelligent tutoring systems. However, interpretation errors are unavoidable and require an effective recovery policy. We describe an evaluation on an error recovery policy in the Beetle II tutorial dialogue system and discuss how different types of interpretation problems affect learning gain and user satisfaction. In particular, the problems arising from student use of non-standard terminology appear to have negative consequences. We argue that existing strategies for dealing with terminology problems are insufficient and that improving such strategies is important in future ITS research.
|
25 |
Importance-Driven Turn-Bidding for Spoken Dialogue Systems
Ethan Selfridge and Peter Heeman
show abstracthide abstractCurrent turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn-Bidding that treats turn-taking as a negotiative process. Each conversant bids for the turn based on the importance of the intended utterance, and Reinforcement Learning is used to indirectly learn this parameter. We find that Importance-Driven Turn-Bidding performs better than two current turn-taking approaches in an artificial collaborative slot-filling domain. The negotiative nature of this model creates efficient dialogues, and supports the improvement of mixed-initiative interaction.
|
26 |
Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
Minwoo Jeong and Ivan Titov
show abstracthide abstractDocuments often have inherently parallel structure: they may consist of a text and commentaries, or an abstract and a body, or parts presenting alternative views on the same problem. Revealing relations between the parts by jointly segmenting and predicting links between the segments, would help to visualize such documents and construct friendlier user interfaces. To address this problem, we propose an unsupervised Bayesian model for joint discourse segmentation and alignment. We apply our method to the “English as a second language” podcast dataset where each episode is composed of two parallel parts: a story and an explanatory lecture. The predicted topical links uncover hidden relations between the stories and the lectures. In this domain, our method achieves competitive results, rivaling those of a previously proposed supervised technique.
|
27 |
Coreference Resolution with Reconcile
Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler and David Hysom
show abstracthide abstractDespite the existence of several noun phrase coreference resolution data sets as well as several formal evaluations on the task, it remains frustratingly difficult to compare results across different coreference resolution systems. This is due to the high cost of implementing a complete end-to-end coreference resolution system, which often forces researchers to substitute available gold-standard information in lieu of implementing a module that would compute that information. Unfortunately, this leads to inconsistent and often unrealistic evaluation scenarios. With the aim to facilitate consistent and realistic experimental evaluations in coreference resolution, we present Reconcile, an infrastructure for the development of learning-based noun phrase (NP) coreference resolution systems. Reconcile is designed to facilitate the rapid creation of coreference resolution systems, easy implementation of new feature sets and approaches to coreference resolution, and empirical evaluation of coreference resolvers across a variety of benchmark data sets and standard scoring metrics. We describe Reconcile and present experimental results showing that Reconcile can be used to create a coreference resolver that achieves performance comparable to state-of-the-art systems on six benchmark data sets.
|
Resources and MT Evaluation
|
28 |
The Manually Annotated Sub-Corpus: A Community Resource for and by the People
Nancy Ide, Collin Baker, Christiane Fellbaum and Rebecca Passonneau
show abstracthide abstractThe Manually Annotated Sub-Corpus (MASC) project provides data and annotations to serve as the base for a community-wide annotation effort of a subset of the American National Corpus. The MASC infrastructure enables the incorporation of contributed annotations into a single, usable format that can then be analyzed as it is or transduced to any of a variety of other formats. MASC includes data from a much wider variety of genres than existing multiply-annotated corpora of English, and the project is committed to a fully open model of distribution, without restriction, for all data and annotations produced or contributed. As such, MASC is the first large-scale, open, community-based effort to create much needed language resources for NLP. This paper describes the MASC project, its corpus and annotations, and serves as a call for contributions of data and annotations from the language processing community.
|
29 |
Correcting Errors in a Treebank Based on Synchronous Tree Substitution Grammar
Yoshihide Kato and Shigeki Matsubara
show abstracthide abstractThis paper proposes a method of correcting annotation errors in a treebank. By using a synchronous grammar, the method transforms parse trees containing annotation errors into the ones whose errors are corrected. The synchronous grammar is automatically induced from the treebank. We report an experimental result of applying our method to the Penn Treebank. The result demonstrates that our method corrects syntactic annotation errors with high precision.
|
30 |
Rebanking CCGbank for Improved NP Interpretation
Matthew Honnibal, James R. Curran and Johan Bos
show abstracthide abstractOnce released, treebanks tend to remain unchanged despite any shortcomings in their depth of linguistic analysis or coverage of specific phenomena. Instead, separate resources are created to address such problems. In this paper we show how to improve the quality of a treebank, by integrating resources and implementing improved analyses for specific constructions. We demonstrate this “rebanking” process by creating an updated version of CCGbank that includes the predicate-argument structure of both verbs and nouns, base-NP brackets, verb-particle constructions, and restrictive and non-restrictive nominal modifiers; and evaluate the impact of these changes on a statistical parser.
|
31 |
BabelNet: Building a Very Large Multilingual Semantic Network
Roberto Navigli and Simone Paolo Ponzetto
show abstracthide abstractIn this paper we present BabelNet – a very large, wide-coverage multilingual semantic network. The resource is automatically constructed by means of a methodology that integrates lexicographic and encyclopedic knowledge from WordNet and Wikipedia. In addition Machine Translation is also applied to enrich the resource with lexical information for all languages. We conduct experiments on new and existing gold-standard datasets to show the high quality and coverage of the resource.
|
32 |
Evaluating Machine Translations Using mNCD
Marcus Dobrinkat, Tero Tapiovaara, Jaakko Väyrynen and Kimmo Kettunen
show abstracthide abstractThis paper introduces mNCD, a method for automatic evaluation of machine translations. The measure is based on normalized compression distance (NCD), a general information theoretic measure of string similarity, and flexible word matching provided by stemming and synonyms. The mNCD measure outperforms NCD in system-level correlation to human judgments in English.
|
33 |
Tackling Sparse Data Issue in Machine Translation Evaluation
Ondřej Bojar, Kamil Kos and David Mareček
show abstracthide abstractWe illustrate and explain problems of n-grams-based machine translation (MT) metrics (e.g. BLEU) when applied to morphologically rich languages such as Czech. A novel metric SemPOS based on the deep-syntactic representation of the sentence tackles the issue and retains the performance for translation to English as well.
|
34 |
Predicate Argument Structure Analysis Using Transformation Based Learning
Hirotoshi Taira, Sanae Fujita and Masaaki Nagata
show abstracthide abstractMaintaining high annotation consistency in large corpora is crucial for statistical learning; however, such work is hard, especially for tasks containing semantic elements. This paper describes predicate argument structure analysis using transformation-based learning. An advantage of transformation-based learning is the readability of learned rules. A disadvantage is that the rule extraction procedure is time-consuming. We present incremental-based, transformation-based learning for semantic processing tasks. As an example, we deal with Japanese predicate argument analysis and show some tendencies of annotators for constructing a corpus with our method.
|
|
37 |
Exemplar-Based Models for Word Meaning in Context
Katrin Erk and Sebastian Pado
show abstracthide abstractThis paper describes ongoing work on distributional models for word meaning in context. We abandon the usual one-vector-per-word paradigm in favor of an exemplar model that activates only relevant occurrences. On a paraphrasing task, we find that a simple exemplar model outperforms more complex state-of-the-art models.
|
38 |
Fully Unsupervised Core-Adjunct Argument Classification
Omri Abend and Ari Rappoport
show abstracthide abstractThe core-adjunct argument distinction is a basic one in the theory of argument structure. The task of distinguishing between the two has strong relations to various basic NLP tasks such as syntactic parsing, semantic role labeling and subcategorization acquisition. This paper presents a novel unsupervised algorithm for the task that uses no supervised models, utilizing instead state-of-the-art syntactic induction algorithms. This is the first work to tackle this task in a fully unsupervised scenario.
|
39 |
A Structured Model for Joint Learning of Argument Roles and Predicate Senses
Yotaro Watanabe, Masayuki Asahara and Yuji Matsumoto
show abstracthide abstractIn predicate-argument structure analysis, it is important to capture non-local dependencies among arguments and inter-dependencies between the sense of a predicate and the semantic roles of its arguments. However, no existing approach explicitly handles both non-local dependencies and semantic dependencies between predicates and arguments. In this paper we propose a structured model that overcomes the limitation of existing approaches; the model captures both types of dependencies simultaneously by introducing four types of factors including a global factor type capturing non-local dependencies among arguments and a pairwise factor type capturing local dependencies between a predicate and an argument. In experiments the proposed model achieved competitive results compared to the state-of-the-art systems without applying any feature selection procedure.
|
40 |
Semantics-Driven Shallow Parsing for Chinese Semantic Role Labeling
Weiwei Sun
show abstracthide abstractOne deficiency of current shallow parsing based Semantic Role Labeling (SRL) methods is that syntactic chunks are too small to effectively group words. To partially resolve this problem, we propose semantics-driven shallow parsing, which takes into account both syntactic structures and predicate-argument structures. We also introduce several new “path” features to improve shallow parsing based SRL method. Experiments indicate that our new method obtains a significant improvement over the best reported Chinese SRL result.
|
41 |
Towards Open-Domain Semantic Role Labeling
Danilo Croce, Cristina Giannone, Paolo Annesi and Roberto Basili
show abstracthide abstractCurrent Semantic Role Labeling technologies are based on inductive algorithms trained over large scale repositories of annotated examples. Frame-based systems currently make use of the FrameNet database but fail to show suitable generalization capabilities in out-of-domain scenarios. In this paper, a state-of-art system for frame-based SRL is extended through the encapsulation of a distributional model of semantic similarity. The resulting argument classification model promotes a simpler feature space that limits the potential overfitting effects. The large scale empirical study here discussed confirms that state-of-art accuracy can be obtained for out-of-domain evaluations.
|
42 |
Collocation Extraction beyond the Independence Assumption
Gerlof Bouma
show abstracthide abstractIn this paper we start to explore two-part collocation extraction association measures that do not estimate expected probabilities on the basis of the independence assumption. We propose two new measures based upon the well-known measures of mutual information and pointwise mutual information. Expected probabilities are derived from automatically trained Aggregate Markov Models. On three collocation gold standards, we find the new association measures vary in their effectiveness.
|
43 |
Automatic Collocation Suggestion in Academic Writing
Jian-Cheng Wu, Yu-Chia Chang, Teruko Mitamura and Jason S. Chang
show abstracthide abstractIn recent years, collocation has been widely acknowledged as an essential characteristic to distinguish native speakers from non-native speakers. Research on academic writing has also shown that collocations are not only common but serve a particularly important discourse function within the academic community. In our study, we propose a machine learning approach to implementing an online collocation writing assistant. We use a data-driven classifier to provide collocation suggestions to improve word choices, based on the result of classification. The system generates and ranks suggestions to assist learners’ collocation usages in their academic writing with satisfactory results.
|
44 |
A Bayesian Method for Robust Estimation of Distributional Similarities
Jun’ichi Kazama, Stijn De Saeger, Kow Kuroda, Masaki Murata and Kentaro Torisawa
show abstracthide abstractExisting word similarity measures are not robust to data sparseness since they rely only on the point estimation of words’ context profiles obtained from a limited amount of data. This paper proposes a Bayesian method for robust distributional word similarities. The method uses a distribution of context profiles obtained by Bayesian estimation and takes the expectation of a base similarity measure under that distribution. When the context profiles are multinomial distributions, the priors are Dirichlet, and the base measure is the Bhattacharyya coefficient, we can derive an analytical form that allows efficient calculation. For the task of word similarity estimation using a large amount of Web data in Japanese, we show that the proposed measure gives better accuracies than other well-known similarity measures.
|
45 |
Improving Chinese Semantic Role Labeling with Rich Syntactic Features
Weiwei Sun
show abstracthide abstractDeveloping features has been shown crucial to advancing the state-of-the-art in Semantic Role Labeling (SRL). To improve Chinese SRL, we propose a set of additional features, some of which are designed to better capture structural information. Our system achieves 93.49 F-measure, a significant improvement over the best reported performance 92.0. We are further concerned with the effect of parsing in Chinese SRL. We empirically analyze the two-fold effect, grouping words into constituents and providing syntactic information. We also give some preliminary linguistic explanations.
|
|
46 |
Unsupervised Ontology Induction from Text
Hoifung Poon and Pedro Domingos
show abstracthide abstractExtracting knowledge from unstructured text is a long-standing goal of NLP. Although learning approaches to many of its subtasks have been developed (e.g., parsing, taxonomy induction, information extraction), all end-to-end solutions to date require heavy supervision and/or manual engineering, limiting their scope and scalability. We present OntoUSP, a system that induces and populates a probabilistic ontology using only dependency-parsed text as input. OntoUSP builds on the USP unsupervised semantic parser by jointly forming ISA and IS-PART hierarchies of lambda-form clusters. The ISA hierarchy allows more general knowledge to be learned, and the use of smoothing for parameter estimation. We evaluate OntoUSP by using it to extract a knowledge base from biomedical abstracts and answer questions. OntoUSP improves on the recall of USP by 47% and greatly outperforms previous state-of-the-art approaches.
|
47 |
Automatically Generating Term Frequency Induced Taxonomies
Karin Murthy, Tanveer A Faruquie, L Venkata Subramaniam, Hima Prasad K and Mukesh Mohania
show abstracthide abstractWe propose a novel method to automatically acquire a term-frequency-based taxonomy from a corpus using an unsupervised method. A term-frequency-based taxonomy is useful for application domains where the frequency with which terms occur on their own and in combination with other terms imposes a natural term hierarchy. We highlight an application for our approach and demonstrate its effectiveness and robustness in extracting knowledge from real-world data.
|
48 |
Complexity Assumptions in Ontology Verbalisation
Richard Power
show abstracthide abstractWe describe the strategy currently pursued for verbalising OWL ontologies by sentences in Controlled Natural Language (i.e., combining *generic* rules for realising logical patterns with *ontology-specific* lexicons for realising atomic terms for individuals, classes, and properties) and argue that its success depends on assumptions about the complexity of terms and axioms in the ontology. We then show, through analysis of a corpus of ontologies, that although these assumptions could in principle be violated, they are overwhelmingly respected in practice by ontology developers.
|
|
49 |
Challenge Paper: Cognitively Plausible Models of Human Language Processing
Frank Keller
show abstracthide abstractWe pose the development of cognitively plausible models of human language processing as a challenge for computational linguistics. Existing models can only deal with isolated phenomena (e.g., garden paths) on small, specifically selected data sets. The challenge is to build models that integrate multiple aspects of human language processing at the syntactic, semantic, and discourse level. Like human language processing, these models should be incremental, predictive, broad coverage, and robust to noise. This challenge can only be met if standardized data sets and evaluation measures are developed.
|
50 |
Syntactic and Semantic Factors in Processing Difficulty: An Integrated Measure
Jeff Mitchell, Mirella Lapata, Vera Demberg and Frank Keller
show abstracthide abstractThe analysis of reading times can provide insights into the processes that underlie language comprehension, with longer reading times indicating greater cognitive load. There is evidence that the language processor is highly predictive, such that prior context allows upcoming linguistic material to be anticipated. Previous work has investigated the contributions of semantic and syntactic contexts in isolation, essentially treating them as independent factors. In this paper we analyze reading times in terms of a single predictive measure which integrates a model of semantic composition with an incremental parser and a language model.
|
11:55–13:15 |
|
53 |
Mood Patterns and Affective Lexicon Access in Weblogs
Thin Nguyen
show abstracthide abstractThe emergence of social media brings chances, but also challenges, to linguistic analysis. In this paper we investigate a novel problem of discovering patterns based on emotion and the association of moods and affective lexicon usage in blogosphere, a representative for social media. We propose the use of normative emotional scores for English words in combination with a psychological model of emotion measurement and a nonparametric clustering process for inferring meaningful emotion patterns automatically from data. Our results on a dataset consisting of more than 17 million mood-groundtruthed blogposts have shown interesting evidence of the emotion patterns automatically discovered that match well with the core-affect emotion model theorized by psychologists. We then present a method based on information theory to discover the association of moods and affective lexicon usage in the new media.
|
54 |
Growing Related Words from Seed via User Behaviors: A Re-ranking Based Approach
Yabin Zheng, Zhiyuan Liu and Lixing Xie
show abstracthide abstractMotivated by Google Sets, we study the problem of growing related words from a single seed word by leveraging user behaviors hiding in user records of Chinese input method. Our proposed method is motivated by the observation that the more frequently two words co-occur in user records, the more related they are. First, we utilize user behaviors to generate candidate words. Then, we utilize search engine to enrich candidate words with adequate semantic features. Finally, we reorder candidate words according to their semantic relatedness to the seed word. Experimental results on a Chinese input method dataset show that our method gains better performance.
|
55 |
Transition-Based Parsing with Confidence-Weighted Classification
Martin Haulrich
show abstracthide abstractWe show that using confidence-weighted classification in transition-based parsing gives results comparable to using SVMs with faster training and parsing time. We also compare with other online learning algorithms and investigate the effect of pruning features when using confidence-weighted classification.
|
56 |
Expanding Verb Coverage in Cyc With VerbNet
Clifton McFate
show abstracthide abstractA robust dictionary of semantic frames is an essential element of natural language understanding systems that use ontologies. However, creating lexical resources that accurately capture semantic representations en masse is a persistent problem. Where the sheer amount of content makes hand creation inefficient, computerized approaches often suffer from over generality and difficulty with sense disambiguation. This paper describes a semi-automatic method to create verb semantic frames in the Cyc ontology by converting the information contained in VerbNet into a Cyc usable format. This method captures the differences in meaning between types of verbs, and uses existing connections between WordNet, VerbNet, and Cyc to specify distinctions between individual verbs when available. This method provides 27,909 frames to OpenCyc which currently has none and can be used to extend ResearchCyc as well. We show that these frames lead to a 20% increase in sample sentences parsed over the Research Cyc verb lexicon.
|
57 |
A Framework for Figurative Language Detection Based on Sense Differentiation
Daria Bogdanova
show abstracthide abstractVarious text mining algorithms require the process of feature selection. High-level semantically rich features, such as figurative language uses, speech errors etc., are very promising for such problems as e.g. writing style detection, but automatic extraction of such features is a big challenge. In this paper, we propose a framework for figurative language use detection. This framework is based on the idea of sense differentiation. We describe two algorithms illustrating the mentioned idea. We show then how these algorithms work by applying them to Russian language data.
|
58 |
Automatic Selectional Preference Acquisition for Latin verbs
Barbara McGillivray
show abstracthide abstractWe present a system that automatically induces Selectional Preferences (SPs) for Latin verbs from two treebanks by using Latin WordNet. Our method overcomes some of the problems connected with data sparseness and the small size of the input corpora. We also suggest a way to evaluate the acquired SPs on unseen events extracted from other Latin corpora.
|
59 |
Edit Tree Distance Alignments for Semantic Role Labelling
Hector-Hugo Franco-Penya
show abstracthide abstract“Tree SRL system” is a Semantic Role Label-ling supervised system based on a tree-distance algorithm and a simple k-NN implementation. The novelty of the system lies in comparing the sentences as tree structures with multiple rela-tions, instead of extracting vectors of features for each relation and classifying them. The sys-tem was tested with the English CoNLL-2009 shared task data set where 79% accuracy was obtained.
|
60 |
Automatic Sanskrit Segmentizer Using Finite State Transducers
Vipul Mittal
show abstracthide abstractIn this paper, we propose a novel method for automatic segmentation of a Sanskrit string into different words. The input for our segmentizer is a Sanskrit string either encoded as a Unicode string or as a Roman transliterated string and the output is a set of possible splits with saliency associated with each of them. We followed two different approaches to segment a Sanskrit text using sandhi rules extracted from a parallel corpus of manually sandhi split text. While the first approach augments the finite state transducer used to analyze Sanskrit morphology and traverse it to segment a word, the second approach generates all possible segmentations and validates each constituent using a morph analyzer.
|
61 |
Adapting Self-training for Semantic Role Labeling
Rasoul Samad Zadeh Kaljahi
show abstracthide abstractSupervised semantic role labeling (SRL) systems trained on hand-crafted annotated corpora have recently achieved state-of-the-art performance. However, creating such corpora is tedious and costly, with the resulting corpora not sufficiently representative of the language. This paper describes a part of an ongoing work on applying bootstrapping methods to SRL to deal with this problem. Previous work shows that, due to the complexity of SRL, this task is not straight forward. One major difficulty is the propagation of classification noise into the successive iterations. We address this problem by employing balancing and preselection methods for self-training, as a bootstrapping algorithm. The proposed methods could achieve improvement over the base line, which do not use these methods.
|
62 |
Weakly Supervised Learning of Presupposition Relations between Verbs
Galina Tremper
show abstracthide abstractPresupposition relations between verbs are not very well covered in existing lexical semantic resources. We propose a weakly supervised algorithm for learning presupposition relations between verbs that distinguishes five semantic relations: presupposition, entailment, temporal inclusion, antonymy and other/no relation. We start with a number of seed verb pairs selected manually for each semantic relation and classify unseen verb pairs. Our algorithm achieves an overall accuracy of 36% for type-based classification.
|
63 |
Importance of Linguistic Constraints in Statistical Dependency Parsing
Bharat Ram Ambati
show abstracthide abstractStatistical systems with high accuracy are very useful in real-world applications. If these systems can capture basic linguistic information, then the usefulness of these statistical systems improve a lot. This paper is an attempt at incorporating linguistic constraints in statistical dependency parsing. We consider a simple linguistic constraint that a verb should not have multiple subjects/objects as its children in the dependency tree. We first describe the importance of this constraint considering Machine Translation systems which use dependency parser output, as an example application. We then show how the current state-of-the-art dependency parsers violate this constraint. We present two new methods to handle this constraint. We evaluate our methods on the state-of-the-art dependency parsers for Hindi and Czech.
|
64 |
The Use of Formal Language Models in the Typology of the Morphology of Amerindian Languages
Andres Osvaldo Porta
show abstracthide abstractThe aim of this work is to present some preliminary results of an investigation in course on the typology of the morphology of the native South American languages from the point of view of the formal language theory. With this object, we give two contrasting examples of descriptions of two Aboriginal languages finite verb forms morphology: Argentinean Quechua (quichua santiagueño) and Toba. The description of the morphology of the finite verb forms of Argentinean Quechua uses finite automata and finite transducers. In this case the construction is straightforward using two level morphology and then, describes in a very natural way the Argentinean Quechua morphology using a regular language. On the contrary, the Toba verbs morphology, with a system that uses simultaneously prefixes and suffixes, has not a natural description as regular language. Toba has a complex system of causative suffixes, whose successive applications determinate the use of prefixes belonging different person marking prefix sets. We adopt the solution of Creider et al. (1995) to naturally deal with this and other similar morphological processes which involve interactions between prefixes and suffixes and then we describe the toba morphology using linear context-free languages and two-taped automata.
|
65 |
Non-Cooperation in Dialogue
Brian Plüss
show abstracthide abstractThis paper presents ongoing research on computational models for non-cooperative dialogue. We start by analysing different levels of cooperation in conversation. Then, inspired by findings from an empirical study, we propose a technique for measuring non-cooperation in political interviews. Finally, we describe a research programme towards obtaining a suitable model and discuss previous accounts for conflictive dialogue, identifying the differences with our work.
|
66 |
Towards Relational POMDPs for Adaptive Dialogue Management
Pierre Lison
show abstracthide abstractOpen-ended spoken interactions are typically characterised by both structural complexity and high levels of uncertainty, making dialogue management in such settings a particularly challenging problem. Traditional approaches have focused on providing theoretical accounts for either the uncertainty or the complexity of spoken dialogue, but rarely considered the two issues simultaneously. This paper describes ongoing work on a new approach to dialogue management which attempts to fill this gap. We represent the interaction as a Partially Observable Markov Decision Process (POMDP) over a rich state space incorporating both dialogue, user, and environment models. The tractability of the resulting POMDP can be preserved using a mechanism for dynamically constraining the action space based on prior knowledge over locally relevant dialogue structures. These constraints are encoded in a small set of general rules expressed as a Markov Logic network. The first-order expressivity of Markov Logic enables us to leverage the rich relational structure of the problem and efficiently abstract over large regions of the state and action spaces.
|
67 |
WSD as a Distributed Constraint Optimization Problem
Siva Reddy and Abhilash Inumella
show abstracthide abstractThis work models Word Sense Disambiguation (WSD) problem as a Distributed Constraint Optimization Problem (DCOP). To model WSD as a DCOP, we view information from various knowledge sources as constraints. DCOP algorithms have the remarkable property to jointly maximize over a wide range of utility functions associated with these constraints. We show how utility functions can be designed for various knowledge sources. For the purpose of evaluation, we modelled all words WSD as a simple DCOP problem. The results are competitive with state-of-art knowledge based systems.
|
68 |
A Probabilistic Generative Model for an Intermediate Constituency-Dependency Representation
Federico Sangati
show abstracthide abstractWe present a probabilistic model extension to the Tesnière Dependency Structure (TDS) framework formulated in (Sangati and Mazza, 2009). This representation incorporates aspects from both constituency and dependency theory. In addition, it makes use of junction structures to handle coordination constructions. We test our model on parsing the English Penn WSJ treebank using a re-ranking framework. This technique allows us to efficiently test our model without needing a specialized parser, and to use the standard evaluation metric on the original Phrase Structure version of the treebank. We obtain encouraging results: we achieve a small improvement over state-of-the-art results when re-ranking a small number of candidate structures, on all the evaluation metrics except for chunking.
|
69 |
Sentiment Translation through Lexicon Induction
Christian Scheible
show abstracthide abstractThe translation of sentiment information is a task from which sentiment analysis systems can benefit. We present a novel, graph-based approach using SimRank, a well-established vertex similarity algorithm to transfer sentiment information between a source language and a target language graph. We evaluate this method in comparison with SO-PMI (Turney, 2002) against a test set which was annotated by 9 human judges. To compare the two methods to the human raters, we first examine the correlation coefficients. The correlation coefficients between the automatic systems and the human ratings, the two methods yield correlation coefficients which are not significantly different, thus SO and SR have about the same performance on this broad measure. Since many adjectives do not express sentiment at all, the correct categorization of neutral adjectives is just as important as the scalar rating. Thus, we divide the adjectives into three categories – positive, neutral, and negative – with a varying threshold between those categories. Overall, SimRank performs better than SO-PMI for a plausible neutral threshold on the human ratings.
|
70 |
Unsupervised Search for The Optimal Segmentation for Statistical Machine Translation
Coşkun Mermer and Ahmet Afşın Akın
show abstracthide abstractWe tackle the previously unaddressed problem of unsupervised determination of the optimal morphological segmentation for statistical machine translation (SMT) and propose a segmentation metric that takes into account both sides of the SMT training corpus. We formulate the objective function as the posterior probability of the training corpus according to a generative segmentation-translation model. We describe how the IBM Model-1 translation likelihood can be computed incrementally between adjacent segmentation states for efficient computation. Submerging the proposed segmentation method in an SMT task from morphologically-rich Turkish to English does not exhibit the expected improvement in translation BLEU scores and confirms the robustness of phrase-based SMT to translation unit combinatorics. A positive outcome of this work is the described modification to the sequential search algorithm of Morfessor (Creutz and Lagus, 2007) that enables arbitrary-fold parallelization of the computation, which unexpectedly improves the translation performance as measured by BLEU.
|
71 |
How Spoken Language Corpora can Refine Current Speech Motor Training Methodologies
Daniil Umanski and Federico Sangati
show abstracthide abstractThe growing availability of spoken language corpora presents new opportunities for enriching the methodologies of speech and language therapy. In this paper, we present a novel approach for constructing speech motor exercises, based on linguistic knowledge extracted from spoken language corpora. In our study with the Dutch Spoken Corpus, syllabic inventories were obtained by means of automatic syllabification of the spoken language data. Our experimental syllabification method exhibited a reliable performance, and allowed for the acquisition of syllabic tokens from the corpus. Consequently, the syllabic tokens were integrated in a tool for clinicians, a result which holds the potential of contributing to the current state of speech motor training methodologies.
|
Question Answering and Entailment
|
01 |
Metadata-Aware Measures for Answer Summarization in Community Question Answering
Mattia Tomasoni and Minlie Huang
show abstracthide abstractOur paper presents a framework for automatically processing information coming from community Question Answering (cQA) portals with the purpose of generating a trustful, complete, relevant and succinct summary of answers posted by users. We exploit the metadata intrinsically present in User Generated Content (UGC) to bias automatic multi-document summarization techniques toward high quality information. We adopt a representation of concepts alternative to n-grams and propose two concept-scoring functions based on semantic overlap. Experimental results on data drawn from Yahoo!\ Answers demonstrate the effectiveness of our method in terms of ROUGE scores. We show that the information contained in the best answers voted by users of cQA portals can be successfully complemented by our method.
|
02 |
Optimizing Question Answering Accuracy by Maximizing Log-Likelihood
Matthias H. Heie, Edward W. D. Whittaker and Sadaoki Furui
show abstracthide abstractIn this paper we demonstrate that there is a strong correlation between the Question Answering (QA) accuracy and the log-likelihood of the answer typing component of our statistical QA model. We exploit this observation in a clustering algorithm which optimizes QA accuracy by maximizing the log-likelihood of a set of question-and-answer pairs. Experimental results show that we achieve better QA accuracy using the resulting clusters than by using manually derived clusters.
|
03 |
Generating Entailment Rules from FrameNet
Roni Ben Aharon, Idan Szpektor and Ido Dagan
show abstracthide abstractMany NLP tasks need accurate knowledge for semantic inference. To this end, mostly WordNet is utilized. Yet WordNet is limited, especially for inference between predicates. To help filling this gap, we present an algorithm that generates inference rules between predicates from FrameNet. Our experiment shows that the novel resource is effective and complements WordNet in terms of rule coverage.
|
04 |
Don’t ‘Have a Clue’? Unsupervised Co-Learning of Downward-Entailing Operators.
Cristian Danescu-Niculescu-Mizil and Lillian Lee
show abstracthide abstractResearchers in textual entailment have begun to consider inferences involving downward-entailing operators, an interesting and important class of lexical items that change the way inferences are made. Recent work proposed a method for learning English downward-entailing operators that requires access to a high-quality collection of negative polarity items (NPIs). However, English is one of the very few languages for which such a list exists. We propose the first approach that can be applied to the many languages for which there is no pre-existing hight-precision database of NPIs. As a case study, we apply our method to Romanian and show that our method yields good results. Also, we perform a cross-linguistic analysis that suggests interesting connections to some findings in linguistic typology.
|
|
05 |
Vocabulary Choice as an Indicator of Perspective
Beata Beigman Klebanov, Eyal Beigman and Daniel Diermeier
show abstracthide abstractWe establish the following characteristics of the task of perspective classification: (a) using term frequencies in a document does not improve classification achieved with absence/presence features; (b) for datasets allowing the relevant comparisons, a small number of top features is found to be as effective as the full feature set and indispensable for the best achieved performance, testifying to the existence of perspective-specific keywords. We relate our findings to research on word frequency distributions and to discourse analytic studies of perspective.
|
06 |
Cross Lingual Adaptation: An Experiment on Sentiment Classifications
Bin Wei and Christopher Pal
show abstracthide abstractIn this paper, we study the problem of using an annotated corpus in English for the same natural language processing task in another language. While various machine translation systems are available, automated translation is still far from perfect. To minimize the noise introduced by translations, we propose to use only key ‘reliable" parts from the translations and apply structural correspondence learning (SCL) to find a low dimensional representation shared by the two languages. We perform experiments on an English-Chinese sentiment classification task and compare our results with a previous co-training approach. To alleviate the problem of data sparseness, we create extra pseudo-examples for SCL by making queries to a search engine. Experiments on real-world on-line review data demonstrate the two techniques can effectively improve the performance compared to previous work.
|
07 |
Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews
Niklas Jakob and Iryna Gurevych
show abstracthide abstractCurrent work on automatic opinion mining has ignored opinion targets expressed by anaphorical pronouns, thereby missing a significant number of opinion targets. In this paper we empirically evaluate whether using an off-the-shelf anaphora resolution algorithm can improve the performance of a baseline opinion mining system. We present an analysis based on two different anaphora resolution systems. Our experiments on a movie review corpus demonstrate, that an unsupervised anaphora resolution algorithm significantly improves the opinion target extraction. We furthermore suggest domain and task specific extensions to an off-the-shelf algorithm which in turn yield significant improvements.
|
08 |
Hierarchical Sequential Learning for Extracting Opinions and Their Attributes
Yejin Choi and Claire Cardie
show abstracthide abstractAutomatic opinion recognition involves a number of related tasks, such as identifying the boundaries of opinion expression, determining their polarity, and determining their intensity. Although much progress has been made in this area, existing research typically treats each of the above tasks in isolation. In this paper, we apply a hierarchical parameter sharing technique using Conditional Random Fields for fine-grained opinion analysis, jointly detecting the boundaries of opinion expressions as well as determining two of their key attributes - polarity and intensity. Our experimental results show that our proposed approach improves the performance over a baseline that does not exploit hierarchical structure among the classes. In addition, we find that the joint approach outperforms a baseline that is based on cascading two separate components.
|
09 |
Last but Definitely Not Least: On the Role of the Last Sentence in Automatic Polarity-Classification
Israela Becker and Vered Aharonson
show abstracthide abstractTwo psycholinguistic and psychophysical experiments show that in order to efficiently extract polarity of written texts such as customer reviews on the Internet, one should concentrate computational efforts on messages in the final position of the text.
|
10 |
Automatically Generating Annotator Rationales to Improve Sentiment Classification
Ainur Yessenalina, Yejin Choi and Claire Cardie
show abstracthide abstractOne of the central challenges in sentiment-based text categorization is that not every portion of a document is equally informative for inferring the overall sentiment of the document. Previous research has shown that enriching the sentiment labels with human annotators’ “rationales” can produce substantial improvements in categorization performance (Zaidan et al., 2007). We explore methods to automatically generate annotator rationales for document-level sentiment classification. Rather unexpectedly, we find the automatically generated rationales just as helpful as human rationales.
|
|
11 |
A Hybrid Rule/Model-Based Finite-State Framework for Normalizing SMS Messages
Richard Beaufort, Sophie Roekhaut, Louise-Amélie Cougnon and Cédrick Fairon
show abstracthide abstractIn recent years, research in natural language processing focused more and more on normalizing text messages. Several approaches were proposed, based either on standard spelling correction technics, translation models or speech recognition methods. However, the problem remains far from being solved: best systems achieve an accuracy of at best 60% at the sentence level, with a word error rate of at least 10%. In this paper, we present a hybrid approach, which combines both linguistics and statistics. The system involves four steps: a rule-based preprocessing, which splits the text into labeled units, like URLs or phones, and unlabeled parts, potentially noisy; a normalization step, relying on statistical models and exclusively performed on the unlabeled parts of the text; a morphosyntactic analysis of the normalized text; finally, a print step, which observes typography rules to build correct sentences, guided by the pieces of information provided by the linguistic analysis. The whole system, based on weighted finite-state machines, is part and parcel of a text-to-speech synthesis system.
|
12 |
Letter-Phoneme Alignment: An Exploration
Sittichai Jiampojamarn and Grzegorz Kondrak
show abstracthide abstractLetter-phoneme alignment is usually generated by a straightforward application of the EM algorithm. We explore several alternative alignment methods that employ phonetics, integer programming, and sets of constraints, and propose a novel approach of refining the EM alignment by aggregation of best alignments. We perform both intrinsic and extrinsic evaluation of the assortment of methods. We show that our proposed EM-Aggregation algorithm leads to the improvement of the state of the art in letter-to-phoneme conversion on several different data sets.
|
13 |
Jointly Optimizing a Two-Step Conditional Random Field Model for Machine Transliteration and Its Fast Decoding Algorithm
Dong Yang, Paul Dixon and Sadaoki Furui
show abstracthide abstractThis paper presents a joint optimization method of a two-step conditional random field (CRF) model for machine transliteration and a fast decoding algorithm for the proposed method. Our method lies in the category of direct orthographical mapping (DOP) between two languages without using any intermediate phonemic mapping. In the two-step CRF model, the first CRF segments an input word into chunks and the second one converts each chunk into one unit in the target language. In this paper, we propose a method to jointly optimize the two-step CRFs and also a fast algorithm to realize it. Our experiments show that the proposed method outperforms the well-known joint source channel model (JSCM) and our proposed fast algorithm decreases the decoding time significantly. Furthermore, combination of the proposed method and the JSCM gives further improvement, which outperforms state-of-the-art results in terms of top-1 accuracy.
|
14 |
Simultaneous Tokenization and Part-Of-Speech Tagging for Arabic without a Morphological Analyzer
Seth Kulick
show abstracthide abstractWe describe an approach to simultaneous tokenization and part-of-speech tagging that is based on separating the closed and open-class items, and focusing on the likelihood of the possible stems of the open-class words. By encoding some basic linguistic information, the machine learning task is simplified, while achieving state-of-the-art tokenization results and competitive POS results, although with a reduced tag set and some evaluation difficulties.
|
|
15 |
Domain Adaptation of Maximum Entropy Language Models
Tanel Alumäe and Mikko Kurimo
show abstracthide abstractWe investigate a recently proposed Bayesian adaptation method for building style-adapted maximum entropy language models for speech recognition, given a large corpus of written language data and a small corpus of speech transcripts. Experiments show that the method consistently outperforms linear interpolation which is typically used in such cases.
|
16 |
Decision Detection Using Hierarchical Graphical Models
Trung H. Bui and Stanley Peters
show abstracthide abstractWe investigate hierarchical graphical models (HGMs) for automatically detecting decisions in multi-party discussions. Several types of dialogue act (DA) are distinguished on the basis of their roles in formulating decisions. HGMs enable us to model dependencies between observed features of discussions, decision DAs, and subdialogues that result in a decision. For the task of detecting decision regions, an HGM classifier outperforms non-hierarchical graphical models and support vector machines, raising the F1-score to 0.80 from 0.55.
|
17 |
Now, Where Was I? Resumption Strategies for an In-Vehicle Dialogue System
Jessica Villing
show abstracthide abstractIn-vehicle dialogue systems often contain more than one application, e.g. a navigation and a telephone application. This means that the user might, for example, interrupt the interaction with the telephone application to ask for directions from the navigation application, and then resume the dialogue with the telephone application. In this paper we present an analysis of interruption and resumption behaviour in human-human in-vehicle dialogues and also propose some implications for resumption strategies in an in-vehicle dialogue system.
|
18 |
Using Speech to Reply to SMS Messages While Driving: An In-Car Simulator User Study
Yun-Cheng Ju and Tim Paek
show abstracthide abstractSpeech recognition affords automobile drivers a hands-free, eyes-free method of replying to Short Message Service (SMS) text messages. Although a voice search approach based on template matching has been shown to be more robust to the challenging acoustic environment of automobiles than using dictation, users may have difficulties verifying whether SMS response templates match their intended meaning, especially while driving. Using a high-fidelity driving simulator, we compared dictation for SMS replies versus voice search in increasingly difficult driving conditions. Although the two approaches did not differ in terms of driving performance measures, users made about six times more errors on average using dictation than voice search.
|
19 |
Learning to Follow Navigational Directions
Adam Vogel and Daniel Jurafsky
show abstracthide abstractWe present a system that learns to follow navigational natural language directions. Where traditional models learn from linguistic annotation or word distributions, our approach is grounded in the world, learning only from routes through a map paired with English descriptions. Lacking an explicit alignment between the text and the reference path makes it difficult to determine what portions of the language describe which aspects of the route. We learn this correspondence with a reinforcement learning algorithm, using the deviation of the route we follow from the intended path as a reward signal. We demonstrate that our system successfully grounds the meaning of spatial terms like ’above’ and ’south’ into geometric properties of paths.
|
20 |
Classification of Feedback Expressions in Multimodal Data
Costanza Navarretta and Patrizia Paggio
show abstracthide abstractThis paper addresses the issue of how linguistic feedback expressions, prosody and head gestures, i.e. head movements and face expressions, relate to one another in a collection of eight video-recorded Danish map-task dialogues. The study shows that in these data, prosodic features and head gestures significantly improve automatic classification of dialogue act labels for linguistic expressions of feedback.
|
|
21 |
Balancing User Effort and Translation Error in Interactive Machine Translation via Confidence Measures
Jesús González Rubio, Daniel Ortiz Martínez and Francisco Casacuberta
show abstracthide abstractThis work deals with the application of confidence measures within an interactive-predictive machine translation system in order to reduce human effort. If a small loss in translation quality can be tolerated for the shake of efficiency, user effort can be saved by interactively translating only those initial translations which the confidence measure classifies as incorrect. We apply confidence estimation as a way to achieve a balance between user effort savings and final translation error. Empirical results show that our proposal allows to obtain almost perfect translations while significantly reducing user effort.
|
22 |
Improving Arabic-to-English Statistical Machine Translation by Reordering Post-Verbal Subjects for Alignment
Marine Carpuat, Yuval Marton and Nizar Habash
show abstracthide abstractWe study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT). We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difficult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. We therefore propose to reorder VS constructions into SV order for SMT word alignment only. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline and despite noisy parses.
|
23 |
Learning Common Grammar from Multilingual Corpus
Tomoharu Iwata, Daichi Mochihashi and Hiroshi Sawada
show abstracthide abstractWe propose a corpus-based probabilistic framework to extract hidden common syntax across languages from non-parallel multilingual corpora in an unsupervised fashion. For this purpose, we assume a generative model for multilingual corpora, where each sentence is generated from a language dependent probabilistic context-free grammar (PCFG), and these PCFGs are generated from a prior grammar that is common across languages. We also develop a variational method for efficient inference. Experiments on a non-parallel multilingual corpus of eleven languages demonstrate the feasibility of the proposed method.
|
|
24 |
Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data
Jenny Rose Finkel and Christopher D. Manning
show abstracthide abstractOne of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms single-task models learned from the same data, but still underperforms compared to single-task models learned on the more abundant quantities of available single-task annotated data. In this paper we present a novel model which makes use of additional single-task annotated data to improve the performance of a joint model. Our model utilizes a hierarchical prior to link the feature weights for shared features in several single-task models and the joint model. Experiments on joint parsing and named entity recognition, using the OntoNotes corpus, show that our hierarchical joint model can produce substantial gains over a joint model trained on only the jointly annotated data.
|
25 |
Detecting Errors in Automatically-Parsed Dependency Relations
Markus Dickinson
show abstracthide abstractWe outline different methods to detect errors in automatically-parsed dependency corpora, by comparing so-called dependency rules to their representation in the training data and flagging anomalous ones. By comparing each new rule to every relevant rule from training, we can identify parts of parse trees which are likely erroneous. Even the relatively simple methods of comparison we propose show promise for speeding up the annotation process.
|
26 |
Tree-Based Deterministic Dependency Parsing — An Application to Nivre’s Method —
Kotaro Kitagawa and Kumiko Tanaka-Ishii
show abstracthide abstractThis article describes new model of statistical dependency parsing based on hierarchical tree structurization. Nivre’s deterministic model attempts to determine the global sentence structure from a sequence of parsing actions, each of which concerns only two words and their locally relational words, but more of the global structure should be taken into account to decide parsing actions. We solves this problem by applying parsing actions based on tree-based model.All the words necessary for judgment are considered by including words in the trees; the model then chooses the most probable head candidate from each tree. In an evaluation experiment using the Penn Treebank(WSJ), the proposed model achieved higher accuracy than did previous deterministic models. In terms of the ratio of sentences parsed completely, it slightly outperformed McDonald’s optimizing method, which takes account of sibling nodes. Although the proposed model’s time complexity is O(n2), the experimental results demonstrated an average parsing time not much slower than O(n).
|
27 |
Sparsity in Dependency Grammar Induction
Jennifer Gillenwater, Kuzman Ganchev, João Graça, Fernando Pereira and Ben Taskar
show abstracthide abstractA strong inductive bias is essential in unsupervised grammar induction. We explore a particular sparsity bias in dependency grammars that encourages a small number of unique dependency types. Specifically, we investigate sparsity-inducing penalties on the posterior distributions of parent-child POS tag pairs in the posterior regularization (PR) framework of Graça et al. (2007). In experiments with 12 languages, we achieve substantial gains over the standard expectation maximization (EM) baseline, with average improvement in attachment accuracy of 6.3\%. Further, our method outperforms models based on a standard Bayesian sparsity-inducing prior by an average of 4.9\%. On English in particular, we show that our approach improves on several other state-of-the-art techniques.
|
28 |
Top-Down K-Best A* Parsing
Adam Pauls, Dan Klein and Chris Quirk
show abstracthide abstractWe propose a top-down algorithm for extracting $k$-best lists from a parser. Our algorithm, TKA$^*$ is a variant of the $k$-best A$^*$ (KA$^*$) algorithm of \newcite{kbestAstar}. In contrast to KA$^*$, which performs an inside and outside pass before performing $k$-best extraction bottom up, TKA$^*$ performs only the inside pass before extracting $k$-best lists top down. TKA$^*$ maintains the same optimality and efficiency guarantees of KA$^*$, but is simpler to both specify and implement.
|
29 |
Hierarchical A* Parsing with Bridge Outside Scores
Adam Pauls and Dan Klein
show abstracthide abstractHierarchical A$^*$ (HA$^*$) uses of a hierarchy of coarse grammars to speed up parsing without sacrificing optimality. HA$^*$ prioritizes search in refined grammars using Viterbi outside costs computed in coarser grammars. We present Bridge Hierarchical A$^*$ (BHA$^*$), a modified Hierarchial A$^*$ algorithm which computes a novel outside cost called a bridge outside cost. These bridge costs mix finer outside scores with coarser inside scores, and thus constitute tighter heuristics than entirely coarse scores. We show that BHA$^*$ substantially outperforms HA$^*$ when the hierarchy contains only very coarse grammars, while achieving comparable performance on more refined hierarchies.
|
30 |
Using Parse Features for Preposition Selection and Error Detection
Joel Tetreault, Jennifer Foster and Martin Chodorow
show abstracthide abstractWe evaluate the effect of adding parse features to a leading model of preposition usage. Results show a significant improvement in the preposition selection task on native speaker text and modest increments in precision and recall in an ESL error detection task. Analysis of the parser output indicates that it is robust enough in the face of noisy non-native writing to extract useful information.
|
|
31 |
Arabic Named Entity Recognition: Using Features Extracted from Noisy Data
Yassine Benajiba, Imed Zitouni, Mona Diab and Paolo Rosso
show abstracthide abstractBuilding an accurate Named Entity Recognition (NER) system for languages with complex morphology is a challenging task. In this paper, we present research that explores the feature space using both gold and bootstrapped noisy features to build an improved highly accurate Arabic NER system. We bootstrap noisy features by projection from an Arabic-English parallel corpus that is automatically tagged with a baseline NER system. The feature space covers lexical, morphological, and syntactic features. The proposed approach yields an improvement of up to 1.64 F-measure (absolute).
|
32 |
Extracting Sequences from the Web
Anthony Fader, Stephen Soderland and Oren Etzioni
show abstracthide abstractClassical Information Extraction (IE) systems fill slots in domain-specific frames. This paper reports on Seq , a novel open IE system that leverages a domain-independent frame to extract ordered sequences such as presidents of the United States or the most common causes of death in the U.S. Seq leverages regularities about sequences to extract a coherent set of sequences from Web text. Seq nearly doubles the area under the precision-recall curve compared to an extractor that does not exploit these regularities.
|
33 |
An Entity-Level Approach to Information Extraction
Aria Haghighi and Dan Klein
show abstracthide abstractWe present a generative model of template-filling in which coreference resolution and role assignment are jointly determined. Underlying template roles first generate abstract entities, which in turn generate concrete textual mentions. On the standard corporate acquisitions dataset, joint resolution in our entity-level model reduces error over a mention-level discriminative approach by up to 20%.
|
34 |
Using Document Level Cross-Event Inference to Improve Event Extraction
Shasha Liao and Ralph Grishman
show abstracthide abstractEvent extraction is a particularly challenging type of information extraction (IE). Most current event extraction systems rely on local information at the phrase or sentence level. However, this local context may be insufficient to resolve ambiguities in identifying particular types of events; information from a wider scope can serve to resolve some of these ambiguities. In this paper, we use document level information to improve the performance of ACE event extraction. In contrast to previous work, we do not limit ourselves to information about events of the same type, but rather use information about other types of events to make predictions or resolve ambiguities regarding a given event. We learn such relationships from the training corpus and use them to help predict the occurrence of events and event arguments in a text. Experiments show that we can get 9.0% (absolute) gain in trigger (event) classification, and more than 8% gain for argument (role) classification in ACE event extraction.
|
35 |
A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network
Decong Li, Sujian Li, Wenjie Li, Wei Wang and Weiguang Qu
show abstracthide abstractIt is a fundamental and important task to extract key phrases from documents. Generally, phrases in a document are not independent in delivering the content of the document. In order to capture and make better use of their relationships in key phrase extraction, we suggest exploring the Wikipedia knowledge to model a document as a semantic network, where both n-ary and binary relationships among phrases are formulated. Based on a commonly accepted assumption that the title of a document is always elaborated to reflect the content of a document and consequently key phrases tend to have close semantics to the title, we propose a novel semi-supervised key phrase extraction approach in this paper by computing the phrase importance in the semantic network, through which the influence of title phrases is propagated to the other phrases iteratively. Experimental results demonstrate the remarkable performance of this approach.
|
Machine Learning and Statistical Methods
|
37 |
Simple Semi-Supervised Training of Part-Of-Speech Taggers
Anders Søgaard
show abstracthide abstractMost attempts to train part-of-speech taggers on a mixture of labeled and unlabeled data have failed (Abney, 2008). In this work stacking (Wolpert, 1992) is used to reduce tagging to a classification task. This simplifies semi-supervised training considerably. Our prefered semi-supervised method combines tri-training (Li & Zhou, 2005) and disagreement-based co-training. On the Wall Street Journal, we obtain an error reduction of 4.2% with SVMTool (Gimenez & Marquez, 2004).
|
38 |
Efficient Optimization of an MDL-Inspired Objective Function for Unsupervised Part-Of-Speech Tagging
Ashish Vaswani, Adam Pauls and David Chiang
show abstracthide abstractThe Minimum Description Length (MDL) principle is a method for model selection that trades off between the explanation of the data by the model and the complexity of the model itself. Inspired by the MDL principle, we develop an objective function for generative models that captures the description of the data by the model (log-likelihood) and the description of the model (model size). We also develop a efficient general search algorithm based on the MAP-EM framework to optimize this function. Since recent work has shown that minimizing the model size in a Hidden Markov Model for part-of-speech (POS) tagging leads to higher accuracies, we test our approach by applying it to this problem. The search algorithm involves a simple change to EM and achieves high POS tagging accuracies on both English and Italian data sets
|
39 |
SVD and Clustering for Unsupervised POS Tagging
Michael Lamar, Yariv Maron, Mark Johnson and Elie Bienenstock
show abstracthide abstractWe revisit the algorithm of Schütze (1995) for unsupervised part-of-speech tagging. The algorithm uses reduced-rank singular value decomposition followed by clustering to extract latent features from context distributions. As implemented here, it achieves state-of-the-art tagging accuracy at considerably less cost than more recent methods. It can also produce a range of finer-grained taggings, with potential applications to various tasks.
|
40 |
Intelligent Selection of Language Model Training Data
Robert C. Moore and William Lewis
show abstracthide abstractWe address the problem of selecting non-domain-specific language model training data to build auxiliary language models for use in tasks such as machine translation. Our approach is based on comparing the cross-entropy, according to domain-specific and non-domain-specifc language models, for each sentence of the text source used to produce the latter language model. We show that this produces better language models, trained on less data, than both random data selection and two other previously proposed methods.
|
41 |
Blocked Inference in Bayesian Tree Substitution Grammars
Trevor Cohn and Phil Blunsom
show abstracthide abstractLearning a tree substitution grammar is very challenging due to derivational ambiguity. Our recent approach used a Bayesian non-parametric model to induce good derivations from treebanked input (Cohn et al., 2009), biasing towards small grammars composed of small generalisable productions. In this paper we present a novel training method for the model using a blocked Metropolis-Hastings sampler in place of the previous method’s local Gibbs sampler. The blocked sampler makes considerably larger moves than the local sampler and consequently converges in less time. A core component of the algorithm is a grammar transformation which represents an infinite tree substitution grammar in a finite context free grammar. This enables efficient blocked inference for training and also improves the parsing algorithm. Both algorithms are shown to improve parsing accuracy.
|
42 |
Boosting-Based System Combination for Machine Translation
Tong Xiao, Jingbo Zhu, Muhua Zhu and Huizhen Wang
show abstracthide abstractIn this paper, we present a simple and effective method to address the issue of how to generate diversified translation systems from a single Statistical Machine Translation (SMT) engine for system combination. Our method is based on the framework of boosting. First, a sequence of weak translation systems is generated from a baseline system in an iterative manner. Then, a strong translation system is built from the ensemble of these weak translation systems. To adapt boosting to SMT system combination, several key components of the original boosting algorithms are redesigned in this work. We evaluate our method on Chinese-to-English Machine Translation (MT) tasks in three baseline systems, including a phrase-based system, a hierarchical phrase-based system and a syntax-based system. The experimental results on three NIST evaluation test sets show that our method leads to significant improvements in translation accuracy over the baseline systems.
|
43 |
Fine-Grained Genre Classification Using Structural Learning Algorithms
Zhili Wu, Katja Markert and Serge Sharoff
show abstracthide abstractPrior use of machine learning in genre classification used a list of labels as classification categories. However, genre classes are often organised into hierarchies, e.g. covering the subgenres of fiction. In this paper we present a method of using the hierarchy of labels to improve the classification accuracy. As a testbed for this approach we use the Brown Corpus as well as a range of other corpora, including the BNC, HGC and Syracuse. The results are not encouraging: apart from the Brown corpus, the improvements of our structural classifier over the flat one are not statistically significant. We discuss the relation between structural learning performance and the visual and distributional balance of the label hierarchy, suggesting that only balanced hierarchies might profit from structural learning.
|
44 |
Online Generation of Locality Sensitive Hash Signatures
Benjamin Van Durme and Ashwin Lall
show abstracthide abstractMotivated by the recent interest in streaming algorithms for processing large text collections, we revisit the work of Ravichandran et al. (2005) on using the Locality Sensitive Hash (LSH) method of Charikar (2002) to enable fast, approximate comparisons of vector cosine similarity. For the common case of feature updates being additive over a data stream, we show that LSH signatures can be maintained online, without additional approximation error, and with lower memory requirements than when using the standard offline technique.
|
45 |
Distributional Similarity vs. PU Learning for Entity Set Expansion
Xiao-Li Li, Lei Zhang, Bing Liu and See-Kiong Ng
show abstracthide abstractDistributional similarity is a classic tech-nique for entity set expansion, where the system is given a set of seed entities of a particular class, and is asked to expand the set using a corpus to obtain more entities of the same class as represented by the seeds. This paper shows that a machine learning model called positive and unla-beled learning (PU learning) can model the set expansion problem better. Based on the test results of 10 corpora, we show that a PU learning technique outperformed distributional similarity significantly.
|
46 |
Active Learning-Based Elicitation for Semi-Supervised Word Alignment
Vamshi Ambati, Stephan Vogel and Jaime Carbonell
show abstracthide abstractSemi-supervised word alignment aims to improve the accuracy of automatic word alignment by incorporating full or partial manual alignments. Motivated by standard active learning query sampling frameworks such as uncertainty-, margin- and query-by-committee sampling we propose multiple query strategies for the alignment link selection task. Our experiments show that by active selection of uncertain and informative links, we reduce the overall manual effort involved in elicitation of alignment link data for training a semi-supervised word aligner.
|
47 |
An Active Learning Approach to Finding Related Terms
David Vickrey, Oscar Kipersztok and Daphne Koller
show abstracthide abstractWe present a novel system that helps non-experts find sets of similar words. The user begins by specifying one or more seed words. The system then iteratively suggests a series of candidate words, which the user can either accept or reject. Current techniques for this task typically bootstrap a classifier based on a fixed seed set. In contrast, our system involves the user throughout the labeling process, using active learning to intelligently explore the space of similar words. In particular, our system can take advantage of negative examples provided by the user. Our system combines multiple pre-existing sources of similarity data (a standard thesaurus, WordNet, contextual similarity), enabling it to capture many types of similarity groups (“synonyms of crash,” “types of car,” etc.). We evaluate on a hand-labeled evaluation set; our system improves over a strong baseline by 36%.
|
48 |
Learning Better Data Representation Using Inference-Driven Metric Learning
Paramveer S. Dhillon, Partha Pratim Talukdar and Koby Crammer
show abstracthide abstractWe initiate a study comparing effectiveness of the transformed spaces learned by recently proposed supervised, and semi-supervised metric learning algorithms to those generated by previously proposed unsupervised dimensionality reduction methods (e.g., PCA). Through a variety of experiments on different real-world datasets, we find IDML-IT, a semi-supervised metric learning algorithm to be the most effective.
|
|
49 |
A Hybrid Hierarchical Model for Multi-Document Summarization
Asli Celikyilmaz and Dilek Hakkani-Tur
show abstracthide abstractScoring sentences in documents given abstract summaries created by humans is important in extractive multi-document summarization. In this paper, we formulate extractive summarization as a two step learning problem building a generative model for pattern discovery and a regression model for inference. We calculate scores for sentences in document clusters based on their latent characteristics using a hierarchical topic model. Then, using these scores, we train a regression model based on the lexical and structural characteristics of the sentences, and use the model to score sentences of new documents to form a summary. Our system advances current state-of-the-art improving ROUGE scores by ~7%. Generated summaries are less redundant and more coherent based upon manual quality evaluations.
|
50 |
Optimizing Informativeness and Readability for Sentiment Summarization
Hitoshi Nishikawa, Takaaki Hasegawa, Yoshihiro Matsuo and Genichiro Kikui
show abstracthide abstractWe propose a novel algorithm for sentiment summarization that takes account of informativeness and readability, simultaneously. Our algorithm generates a summary by selecting and ordering sentences taken from multiple review texts according to two scores that represent the informativeness and readability of the sentence order. The informativeness score is defined by the number of sentiment expressions and the readability score is learned from the target corpus. We evaluate our method by summarizing reviews on restaurants. Our method outperforms an existing algorithm as indicated by its ROUGE score and human readability experiments.
|
51 |
Wrapping up a Summary: From Representation to Generation
Josef Steinberger, Marco Turchi, Mijail Kabadjov, Ralf Steinberger and Nello Cristianini
show abstracthide abstractThe main focus of this work is to investigate robust ways for generating summaries from summary representations without recurring to simple sentence extraction and aiming at more human-like summaries. This is motivated by empirical evidence from TAC 2009 data showing that human summaries contain on average more and shorter sentences than the system summaries. We report encouraging preliminary results comparable to those attained by participating systems at TAC 2009.
|
15:00–17:35 |
|
73 |
Grammar Prototyping and Testing with the LinGO Grammar Matrix Customization System
Emily M. Bender, Scott Drellishak, Antske Fokkens, Michael Wayne Goodman, Daniel P. Mills, Laurie Poulson and Safiyyah Saleem
show abstracthide abstractThis demonstration presents the LinGO Grammar Matrix grammar customization system: a repository of distilled linguistic knowledge and a web-based service which elicits a typological description of a language from the user and yields a customized grammar fragment ready for sustained development into a broad-coverage grammar. We describe the implementation of this repository with an emphasis on how the information is made available to users, including in-browser testing capabilities.
|
74 |
cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models
Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonathan Weese, Ferhan Ture, Phil Blunsom, Hendra Setiawan, Vladimir Eidelman and Philip Resnik
show abstracthide abstractWe present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation for translation forests, the decoder strictly separates model-specific translation logic from general rescoring, pruning, and inference algorithms. From this unified representation, the decoder can extract not only the 1- or k-best translations, but also alignments to a reference, or the quantities necessary to drive discriminative training using gradient-based or gradient-free optimization techniques. Its efficient C++ implementation means that memory use and runtime performance are significantly better than comparable decoders.
|
75 |
Beetle II: A System for Tutoring and Computational Linguistics Experimentation
Myroslava O. Dzikovska, Johanna D. Moore, Natalie Steinhauser, Gwendolyn Campbell, Elaine Farrow and Charles B. Callaway
show abstracthide abstractWe present Beetle II, a tutorial dialogue system designed to accept unrestricted language input and support experimentation with different tutorial planning and dialogue strategies. Our first ystem evaluation used two different tutorial policies and demonstrated that the system can be successfully used to study the impact of different approaches to tutoring. In the future, the system can also be used to experiment with a variety of natural language interpretation and generation techniques.
|
76 |
GernEdiT - The GermaNet Editing Tool
Verena Henrich and Erhard Hinrichs
show abstracthide abstractGernEdiT (short for: GermaNet Editing Tool) offers a graphical interface for the lexicographers and developers of GermaNet to access and modify the underlying GermaNet resource. GermaNet is a lexical-semantic wordnet that is modeled after the Princeton WordNet for English. The traditional lexicographic development of GermaNet was error prone and time-consuming, mainly due to a complex underlying data format and no opportunity of automatic consistency checks. GernEdiT replaces the earlier development by a more user-friendly tool, which facilitates automatic checking of internal consistency and correctness of the linguistic resource. This paper presents all these core functionalities of GernEdiT along with details about its usage and usability.
|
77 |
WebLicht: Web-Based LRT Services for German
Erhard Hinrichs, Marie Hinrichs and Thomas Zastrow
show abstracthide abstractThis software demonstration presents WebLicht (short for: Web-Based Linguistic Chaining Tool), a web-based service environment for the integration and use of language resources and tools (LRT). WebLicht is being developed as part of the D-SPIN project . We-bLicht is implemented as a web application so that there is no need for users to install any software on their own computers or to concern themselves with the technical details involved in building tool chains. The integrated web services are part of a prototypical infrastructure that was developed to facilitate chaining of LRT services. WebLicht allows the integration and use of distributed web services with standardized APIs. The nature of these open and standardized APIs makes it possible to access the web services from nearly any programming language, shell script or workflow engine (UIMA, Gate etc.) Additionally, an application for integration of additional services is available, allowing anyone to contribute his own web service.
|
78 |
The S-Space Package: An Open Source Package for Word Space Models
David Jurgens and Keith Stevens
show abstracthide abstractWe present the S-Space Package, an open source framework for developing and evaluating word space algorithms. The package implements well-known word space algorithms, such as LSA, and provides a comprehensive set of matrix utilities and data structures for extending new or existing models. The package also includes word space benchmarks for evaluation. Both algorithms and libraries are designed for high concurrency and scalability. We demonstrate the efficiency of the reference implementations and also provide their results on six benchmarks.
|
79 |
Talking NPCs in a Virtual Game World
Tina Klüwer, Peter Adolphs, Feiyu Xu, Hans Uszkoreit and Xiwen Cheng
show abstracthide abstractThe submission describes a system using dialog, information extraction and Semantic Web technologies to enable natural language for Non Player Characters (NPCs) in an online game world. Depending on the type of game, NPCs are often used for enhancing plot and challenges and for making the artificial world more vivid and therefore also more immersive. They can also help to populate new worlds by carrying out jobs the user-led characters come in touch with. The range of functions to be filled by NPCs is currently still strongly restricted by their limited capabilities in autonomous acting and communication. This shortcoming creates a strong need for progress in AI and NLP, especially in the areas of planning and dialogue systems.
|
80 |
An Open-Source Package for Recognizing Textual Entailment
Milen Kouylekov and Matteo Negri
show abstracthide abstractThis paper presents a general-purpose open source package for recognizing Textual Entailment. The system implements a collection of algorithms, providing a configurable framework to quickly set up a working environment to experiment with the RTE task. Fast prototyping of new solutions is also allowed by the possibility to extend its modular architecture. We present the tool as a useful resource to approach the Textual Entailment problem, as an instrument for didactic purposes, and as an opportunity to create a collaborative environment to promote research in the field.
|
81 |
Personalising Speech-To-Speech Translation in the EMIME Project
Mikko Kurimo, William Byrne, John Dines, Philip N. Garner, Matthew Gibson, Yong Guan, Teemu Hirsimäki, Reima Karhila, Simon King, Hui Liang, Keiichiro Oura, Lakshmi Saheer, Matt Shannon, Sayaki Shiota and Jilei Tian
show abstracthide abstractIn the EMIME project we have studied unsupervised cross-lingual speaker adaptation. We have employed an HMM statistical framework for both speech recognition and synthesis which provides transformation mechanisms to adapt the synthesized voice in TTS (text-to-speech) using the recognized voice in ASR (automatic speech recognition). An important application for this research is personalised speech-to-speech translation that will use the voice of the speaker in the input language to utter the translated sentences in the output language. In mobile environments this enhances the users’ interaction across language barriers by making the output speech sound more like the original speaker’s way of speaking, even if she or he could not speak the output language.
|
82 |
Hunting for the Black Swan: Risk Mining from Text
Jochen Leidner and Frank Schilder
show abstracthide abstractIn the business world, analyzing and dealing with risk permeates all decisions and actions. However, to date risk identification, the first step in the risk management cycle, has always been a manual activity with little to no intelligent software tool support. In addition, although companies are required to list risks to their business in their annual SEC filings in the USA, these descriptions are often very high-level and vague. In this paper, we introduce Risk Mining, which is the task of identifying a set of risks pertaining to a business area or entity. We argue that by combining Web mining and Information Extraction (IE) techniques, risks can be detected automatically before they materialize, thus providing valuable business intelligence. We describe a system that induces a risk taxonomy with concrete risks (e.g., interest rate changes) at its leaves and more abstract risks (e.g., financial risks) closer to its root node. The taxonomy is induced via a bootstrapping algorithms starting with a few seeds. The risk taxonomy is used by the system as input to a risk monitor that matches risk mentions in financial documents to the abstract risk types, thus bridging a lexical gap. Our system is able to automatically generate company specific “risk maps”, which we demonstrate for a corpus of earnings report conference calls.
|
83 |
Speech-Driven Access to the Deep Web on Mobile Devices
Taniya Mishra and Srinivas Bangalore
show abstracthide abstractThe Deep Web is the collection of information repositories that are not indexed by search engines. These repositories are typically accessible through web forms and contain dynamically changing information. In this paper, we present a system that allows users to access such rich repositories of information on mobile devices using spoken language.
|
84 |
Tools for Multilingual Grammar-Based Translation on the Web
Aarne Ranta, Krasimir Angelov and Thomas Hallgren
show abstracthide abstractThis is a system demo for a set of tools for translating texts between multiple languages in real time with high quality. The translation works on restricted languages, and is based on semantic interlinguas. The underlying model is GF (Grammatical Framework), which is an open-source toolkit for multilingual grammar implementations. The demo will cover up to 20 parallel languages. Two related sets of tools are presented: grammarian’s tools helping to build translators for new domains and languages, and translator’s tools helping to translate documents. The grammarian’s tools are designed to make it easy to port the technique to new applications. The translator’s tools are essential in the restricted language context, enabling the author to remain in the fragments recognized by the system. The tools that are demonstrated will be applied and developed further in the European project MOLTO (Multilingual On-Line Translation. FP7-ICT-247914), which will start in March 2010 and run for three years.
|
85 |
Demonstration of a Prototype for a Conversational Companion for Reminiscing about Images
Yorick Wilks, Roberta Catizone, Alexiei Dingli and Weiwei Cheng
show abstracthide abstractThis paper describes an initial prototype demonstrator of a Companion, designed as a platform for novel approaches to the following: 1) The use of Information Extraction (IE) techniques to extract the content of incoming dialogue utterances after an Automatic Speech Recognition (ASR) phase, 2) The conversion of the input to Resource Descriptor Format (RDF) to allow the generation of new facts from existing ones, under the control of a Dialogue Manger (DM), that also has access to stored knowledge and to open knowledge accessed in real time from the web, all in RDF form, 3) A DM implemented as a stack and network virtual machine that models mixed initiative in dialogue control, and 4) A tuned dialogue act detector based on corpus evidence. The prototype platform was evaluated, and we describe this briefly; it is also designed to support more extensive forms of emotion detection carried by both speech and lexical content, as well as extended forms of machine learning.
|
86 |
It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text
Zhi Zhong and Hwee Tou Ng
show abstracthide abstractWord sense disambiguation (WSD) systems based on supervised learning achieved the best performance in SensEval and SemEval workshops. However, there are few publicly available open source WSD systems. This limits the use of WSD in other applications, especially for researchers whose research interests are not in WSD. In this paper, we present IMS, a supervised English all-words WSD system. The flexible framework of IMS allows users to integrate different preprocessing tools, additional features, and different classifiers. By default, we use linear support vector machines as the classifier with multiple knowledge-based features. In our implementation, IMS achieves state-of-the-art results on several SensEval and SemEval tasks.
|