In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem’s two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.

Well pre-trained contextualized representations from pre-trained language model (PLM) have been shown helpful for enhancing various natural language processing tasks, surely including neural machine translation (NMT). However, existing methods either consider encoder-only enhancement or rely on specific multilingual PLMs, which leads to a much larger model or give up potentially helpful knowledge from target PLMs. In this paper, we propose a new monolingual PLM-sponsored NMT model to let both encoder and decoder enjoy PLM enhancement to alleviate such obvious inconvenience. Especially, incorporating a newly proposed frequency-weighted embedding transformation algorithm, PLM embeddings can be effectively exploited in terms of the representations of the NMT decoder. We evaluate our model on IWSLT14 En-De, De-En, WMT14 En-De, and En-Fr tasks, and the results show that our proposed PLM enhancement gives significant improvement and even helps achieve new state-of-the-art.

Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. Better evaluation of the semantic distance between the overlapped sentences benefits the language system’s understanding and guides the generation. Since conventional semantic metrics are based on word representations, they are vulnerable to the disturbance of overlapped components with similar representations. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence (LCS) as neighboring words and use masked language modeling (MLM) from pre-trained language models (PLMs) to predict the distributions in their positions. Our metric, Neighboring Distribution Divergence (NDD), represents the semantic distance by calculating the divergence between distributions in the overlapped parts. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts. Based on the discovery, we further implement an unsupervised and training-free method for text compression, leading to a significant improvement on the previous perplexity-based method. The high compression rate controlling ability of our method even enables NDD to outperform the supervised state-of-the-art in domain adaption by a huge margin. Further experiments on syntax and semantics analyses verify the awareness of internal sentence structures, indicating the high potential of NDD for further studies.

Commonsense fact verification, as a challenging branch of commonsense question-answering (QA), aims to verify through facts whether a given commonsense claim is correct or not. Answering commonsense questions necessitates a combination of knowledge from various levels. However, existing studies primarily rest on grasping either unstructured evidence or potential reasoning paths from structured knowledge bases, yet failing to exploit the benefits of heterogeneous knowledge simultaneously. In light of this, we propose Decker, a commonsense fact verification model that is capable of bridging heterogeneous knowledge by uncovering latent relationships between structured and unstructured knowledge. Experimental results on two commonsense fact verification benchmark datasets, CSQA2.0 and CREAK demonstrate the effectiveness of our Decker and further analysis verifies its capability to seize more precious information through reasoning. The official implementation of Decker is available at https://github.com/Anni-Zou/Decker.

Researchers are witnessing knowledge-inspired natural language processing shifts the focus from entity-level to event-level, whereas event coreference resolution is one of the core challenges. This paper proposes a novel model for within-document event coreference resolution. On the basis of event but not entity as before, our model learns and integrates multiple representations from both event alone and event pair. For the former, we introduce multiple linguistics-motivated event alone features for more discriminative event representations. For the latter, we consider multiple similarity measures to capture the distinction of event pair. Our proposed model achieves new state-of-the-art on the ACE 2005 benchmark, demonstrating the effectiveness of our proposed framework.

Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues, is expensive and unattainable for most people. Though previous studies have used powerful LLMs to generate the dialogues automatically, they all suffer from generating untruthful dialogues because of the model hallucination. Therefore, we propose a method called RefGPT to generate enormous truthful and customized dialogues without worrying about factual errors caused by the model hallucination. RefGPT solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues. Additionally, RefGPT adds detailed controls on every utterance to enable high customization capability, which previous studies have ignored. On the basis of RefGPT, we also propose two high-quality dialogue datasets generated by GPT-4, namely **RefGPT-Fact** and **RefGPT-Code**. RefGPT-Fact is a dataset with 100k multi-turn dialogues based on factual knowledge and RefGPT-Code has 76k multi-turn dialogues covering a wide range of coding scenarios. Our code and datasets are released in https://github.com/mutonix/RefGPT.

In open-domain question-answering (ODQA), most existing questions require single-hop reasoning on commonsense. To further extend this task, we officially introduce open-domain multi-hop reasoning (ODMR) by answering multi-hop questions with explicit reasoning steps in open-domain setting. Recently, large language models (LLMs) have found significant utility in facilitating ODQA without external corpus. Furthermore, chain-of-thought (CoT) prompting boosts the reasoning capability of LLMs to a greater extent with manual or automated paradigms. However, existing automated methods lack of quality assurance, while manual approaches suffer from limited scalability and poor diversity, hindering the capabilities of LLMs. In this paper, we propose Self-prompted Chain-of-Thought (SP-CoT), an automated framework to mass-produce high quality CoTs of LLMs, by LLMs and for LLMs. SP-CoT introduces an automated generation pipeline of high quality ODMR datasets, an adaptive sampler for in-context CoT selection and self-prompted inference via in-context learning. Extensive experiments on four multi-hop question-answering benchmarks show that our proposed SP-CoT not only significantly surpasses the previous SOTA methods on large-scale (175B) LLMs, but also nearly doubles the zero-shot performance of small-scale (13B) LLMs. Further analysis reveals the remarkable capability of SP-CoT to elicit direct and concise intermediate reasoning steps by recalling ~50% of intermediate answers on MuSiQue-Ans dataset.

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these models are not capable of generating high-quality text compared with decoder-based causal language models. Can we transform a pre-trained language understanding model into an effective language generation model? We propose a Semantic-Guided Alignment-then-Denoising (SGA) approach to adapt a multilingual encoder to a multilingual generator with a small number of additional parameters. Experiments show that the proposed approach is an effective adaption method, outperforming widely-used initialization-based methods with gains of 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation on XLM-R_large. On the other hand, we observe that XLM-R is still inferior to mBART in supervised settings despite better results on zero-shot settings, indicating that more exploration is required to make understanding models strong generators. Our code is available at https://github.com/chengzhipanpan/XLMR4MT.

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM.

Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data. As opposed to constructing increasingly complex logic, this paper probes into the boolean logic, the root capability of a logical reasoner. We find that any pre-trained language models even including large language models only behave like a random selector in the face of multi-nested boolean logic, a task that humans can handle with ease. To empower language models with this fundamental capability, this paper proposes a new self-supervised learning method Curriculum Logical Reasoning (Clr), where we augment the training data with nested boolean logic chain step-by-step, and program the training from simpler logical patterns gradually to harder ones. This new training paradigm allows language models to effectively generalize to much harder and longer-hop logic, which can hardly be learned through naive training. Furthermore, we show that boolean logic is a great foundation for improving the subsequent general logical tasks.

Dialogue response generation requires an agent to generate a response according to the current dialogue history, in terms of which two-party dialogues have been well studied, but leaving a great gap for multi-party dialogues at the same time. Different from two-party dialogues where each response is a direct reply to its previous utterance, the addressee of a response utterance should be specified before it is generated in the multi-party scenario. Thanks to the huge amount of two-party conversational data, various pre-trained language models for two-party dialogue response generation have been proposed. However, due to the lack of annotated addressee labels in multi-party dialogue datasets, it is hard to use them to pre-train a response generation model for multi-party dialogues. To tackle this obstacle, we propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels, and the maximization steps to optimize a response generation model. Theoretical analyses and extensive experiments have justified the feasibility and effectiveness of our proposed method. The official implementation of this paper is available at https://github.com/EricLee8/MPDRG.

Masked Language Modeling (MLM) has been widely used as the denoising objective in pre-training language models (PrLMs). Existing PrLMs commonly adopt a Random-Token Masking strategy where a fixed masking ratio is applied and different contents are masked by an equal probability throughout the entire training. However, the model may receive complicated impact from pre-training status, which changes accordingly as training time goes on. In this paper, we show that such time-invariant MLM settings on masking ratio and masked content are unlikely to deliver an optimal outcome, which motivates us to explore the influence of time-variant MLM settings. We propose two scheduled masking approaches that adaptively tune the masking ratio and masked content in different training stages, which improves the pre-training efficiency and effectiveness verified on the downstream tasks. Our work is a pioneer study on time-variant masking strategy on ratio and content and gives a better understanding of how masking ratio and masked content influence the MLM pre-training.

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these obstacles, an effective way is to pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. However, due to the lack of explicitly annotated discourse labels in multi-party dialogue corpora, previous works fail to scale up the pre-training process by putting aside the unlabeled multi-party conversational data for nothing. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model by unsupervised latent variable inference methods. Experiments on multiple downstream tasks show that our pre-trained model outperforms strong baselines by large margins and achieves state-of-the-art (SOTA) results, justifying the effectiveness of our method. The official implementation of this paper is available at https://github.com/EricLee8/MPD_EMVI.

In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehensive assessment of the open domain generalization of CSC models. Then, we demonstrate that a very simple strategy – randomly masking 20% non-error tokens from the input sequence during fine-tuning – is sufficient for learning a much better language model without sacrificing the error model. This technique can be applied to any model architecture and achieves new state-of-the-art results on SIGHAN, ECSpell, and LEMON.

Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks and has achieved widespread success. Despite this, UIE models have limitations. For example, they rely heavily on span boundaries in the data during training, which does not reflect the reality of span annotation challenges. Slight adjustments to positions can also meet requirements. Additionally, UIE models lack attention to the limited span length feature in IE. To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework. Specifically, our contribution consists of two concepts: fuzzy span loss and fuzzy span attention. Our experimental results on a series of main IE tasks show significant improvement compared to the baseline, especially in terms of fast convergence and strong performance with small amounts of data and training epochs. These results demonstrate the effectiveness and generalization of FSUIE in different tasks, settings, and scenarios.

Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension.

Training dense passage representations via contrastive learning has been shown effective for Open-Domain Passage Retrieval (ODPR). Existing studies focus on further optimizing by improving negative sampling strategy or extra pretraining. However, these studies keep unknown in capturing passage with internal representation conflicts from improper modeling granularity. Specifically, under our observation that a passage can be organized by multiple semantically different sentences, modeling such a passage as a unified dense vector is not optimal. This work thus presents a refined model on the basis of a smaller granularity, contextual sentences, to alleviate the concerned conflicts. In detail, we introduce an in-passage negative sampling strategy to encourage a diverse generation of sentence representations within the same passage. Experiments on three benchmark datasets verify the efficacy of our method, especially on datasets where conflicts are severe. Extensive experiments further present good transferability of our method across datasets.

Machine reading comprehension is a heavily-studied research and test field for evaluating new pre-trained language models (PrLMs) and fine-tuning strategies, and recent studies have enriched the pre-trained language models with syntactic, semantic and other linguistic information to improve the performance of the models. In this paper, we imitate the human reading process in connecting the anaphoric expressions and explicitly leverage the coreference information of the entities to enhance the word embeddings from the pre-trained language model, in order to highlight the coreference mentions of the entities that must be identified for coreference-intensive question answering in QUOREF, a relatively new dataset that is specifically designed to evaluate the coreference-related performance of a model. We use two strategies to fine-tune a pre-trained language model, namely, placing an additional encoder layer after a pre-trained language model to focus on the coreference mentions or constructing a relational graph convolutional network to model the coreference relations. We demonstrate that the explicit incorporation of coreference information in the fine-tuning stage performs better than the incorporation of the coreference information in pre-training a language model.

As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally; while extractive MRC focuses on higher local boundary preciseness for answer extraction. Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks. To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously. Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components. The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://github.com/Yilin1111/poi-net.

Restricted machine translation incorporates human prior knowledge into translation. It restricts the flexibility of the translation to satisfy the demands of translation in specific scenarios. Existing work typically imposes constraints on beam search decoding. Although this can satisfy the requirements overall, it usually requires a larger beam size and far longer decoding time than unrestricted translation, which limits the concurrent processing ability of the translation model in deployment, and thus its practicality. In this paper, we propose a general training framework that allows a model to simultaneously support both unrestricted and restricted translation by adopting an additional auxiliary training process without constraining the decoding process. This maintains the benefits of restricted translation but greatly reduces the extra time overhead of constrained decoding, thus improving its practicality. The effectiveness of our proposed training framework is demonstrated by experiments on both original (WAT21 En↔Ja) and simulated (WMT14 En→De and En→Fr) restricted translation benchmarks.

Machine reading comprehension (MRC) poses new challenges to logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical connections exist at different granularity levels. However, most existing methods of logical reasoning individually focus on either entity-aware or discourse-based information but ignore the hierarchical relations that may even have mutual effects. This paper proposes a holistic graph network (HGN) that deals with context at both discourse-level and word-level as the basis for logical reasoning to provide a more fine-grained relation extraction. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism to improve the interpretation of MRC systems. Experimental results on logical reasoning QA datasets (ReClor and LogiQA) and natural language inference datasets (SNLI and ANLI) show the effectiveness and generalization of our method, and in-depth analysis verifies its capability to understand complex logical relations.

Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like knowledge bases (KBs), which are usually highly resource consuming in construction. Recently pre-trained language models (PLMs) show effectiveness as an alternative for commonsense clues when they play a role of knowledge generator. However, existing work either relies on large-scale in-domain or out-of-domain labeled data, or fails to generate knowledge of high quality in a general way. Motivated by human thinking experience, we propose an approach of All-round Thinker (ArT) by fully taking association during knowledge generating. In detail, our model first focuses on key parts in the given context, and then generates highly related knowledge on such a basis in an association way like human thinking. Besides, for casual reasoning, a reverse thinking mechanism is especially added to further enhance bidirectional inferring between cause and effect. ArT is totally unsupervised and KBs-free. We evaluate it on three commonsense QA benchmarks: COPA, SocialIQA and SCT. On all scales of PLM backbones, ArT shows its brilliant performance and outperforms previous advanced unsupervised models.

Existing studies typically handle aspect-based sentiment analysis by stacking multiple neural modules, which inevitably result in severe error propagation. Instead, we propose a novel end-to-end framework, MRCOOL: MRC-PrOmpt mOdeL framework, where numerous sentiment aspects are elicited by a machine reading comprehension (MRC) model and their corresponding sentiment polarities are classified in a prompt learning way. Experiments show that our end-to-end framework consistently yields promising results on widely-used benchmark datasets which significantly outperform existing state-of-the-art models or achieve comparable performance.

As a fundamental natural language processing task and one of core knowledge extraction techniques, named entity recognition (NER) is widely used to extract information from texts for downstream tasks. Nested NER is a branch of NER in which the named entities (NEs) are nested with each other. However, most of the previous studies on nested NER usually apply linear structure to model the nested NEs which are actually accommodated in a hierarchical structure. Thus in order to address this mismatch, this work models the full nested NEs in a sentence as a holistic structure, then we propose a holistic structure parsing algorithm to disclose the entire NEs once for all. Besides, there is no research on applying corpus-level information to NER currently. To make up for the loss of this information, we introduce Point-wise Mutual Information (PMI) and other frequency features from corpus-aware statistics for even better performance by holistic modeling from sentence-level to corpus-level. Experiments show that our model yields promising results on widely-used benchmarks which approach or even achieve state-of-the-art. Further empirical studies show that our proposed corpus-aware features can substantially improve NER domain adaptation, which demonstrates the surprising advantage of our proposed corpus-level holistic structure modeling.

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the trade-off between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code.

Abstract Meaning Representation (AMR) offers a unified semantic representation for natural language sentences. Thus transformation between AMR and text yields two transition tasks in opposite directions, i.e., Text-to-AMR parsing and AMR-to-Text generation. Existing AMR studies only focus on one-side improvements despite the duality of the two tasks, and their improvements are greatly attributed to the inclusion of large extra training data or complex structure modifications which harm the inference speed. Instead, we propose data-efficient Bidirectional Bayesian learning (BiBL) to facilitate bidirectional information transition by adopting a single-stage multitasking strategy so that the resulting model may enjoy much lighter training at the same time. Evaluation on benchmark datasets shows that our proposed BiBL outperforms strong previous seq2seq refinements without the help of extra data which is indispensable in existing counterpart models. We release the codes of BiBL at: https://github.com/KHAKhazeus/BiBL.

Deep learning has demonstrated performance advantages in a wide range of natural language processing tasks, including neural machine translation (NMT). Transformer NMT models are typically strengthened by deeper encoder layers, but deepening their decoder layers usually results in failure. In this paper, we first identify the cause of the failure of the deep decoder in the Transformer model. Inspired by this discovery, we then propose approaches to improving it, with respect to model structure and model training, to make the deep decoder practical in NMT. Specifically, with respect to model structure, we propose a cross-attention drop mechanism to allow the decoder layers to perform their own different roles, to reduce the difficulty of deep-decoder learning. For model training, we propose a collapse reducing training approach to improve the stability and effectiveness of deep-decoder training. We experimentally evaluated our proposed Transformer NMT model structure modification and novel training methods on several popular machine translation benchmarks. The results showed that deepening the NMT model by increasing the number of decoder layers successfully prevented the deepened decoder from degrading to an unconditional language model. In contrast to prior work on deepening an NMT model on the encoder, our method can deepen the model on both the encoder and decoder at the same time, resulting in a deeper model and improved performance.

Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs are not robust. However, we find that the adversarial samples that PrLMs fail are mostly non-natural and do not appear in reality. We question the validity of the current evaluation of robustness of PrLMs based on these non-natural adversarial samples and propose an anomaly detector to evaluate the robustness of PrLMs with more natural adversarial samples. We also investigate two applications of the anomaly detector: (1) In data augmentation, we employ the anomaly detector to force generating augmented data that are distinguished as non-natural, which brings larger gains to the accuracy of PrLMs. (2) We apply the anomaly detector to a defense framework to enhance the robustness of PrLMs. It can be used to defend all types of attacks and achieves higher accuracy on both adversarial samples and compliant samples than other defense frameworks.

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.

Multiple pre-training objectives fill the vacancy of the understanding capability of single-objective language modeling, which serves the ultimate purpose of pre-trained language models (PrLMs), generalizing well on a mass of scenarios. However, learning multiple training objectives in a single model is challenging due to the unknown relative significance as well as the potential contrariety between them. Empirical studies have shown that the current objective sampling in an ad-hoc manual setting makes the learned language representation barely converge to the desired optimum. Thus, we propose MOMETAS, a novel adaptive sampler based on meta-learning, which learns the latent sampling pattern on arbitrary pre-training objectives. Such a design is lightweight with negligible additional training overhead. To validate our approach, we adopt five objectives and conduct continual pre-training with BERT-base and BERT-large models, where MOMETAS demonstrates universal performance gain over other rule-based sampling strategies on 14 natural language processing tasks.

Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.

Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However, contrastive objectives which dominate the current sentence representation learning bring little linguistic interpretability and no performance guarantee on downstream semantic tasks. We instead propose a novel generative self-supervised learning objective based on phrase reconstruction. To overcome the drawbacks of previous generative methods, we carefully model intra-sentence structure by breaking down one sentence into pieces of important phrases. Empirical studies show that our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods not only on the STS benchmarks, but also on downstream semantic retrieval and reranking tasks. Our code is available at https://github.com/chengzhipanpan/PaSeR.

Discontinuous constituency parsing is still kept developing for its efficiency and accuracy are far behind its continuous counterparts. Motivated by the observation that a discontinuous constituent tree can be simply transformed into a pseudo-continuous one by artificially reordering words in the sentence, we propose a novel reordering method, thereby construct fast and accurate discontinuous constituency parsing systems working in continuous way. Specifically, we model the relative position changes of words as a list of actions. By parsing and performing this actions, the corresponding pseudo-continuous sequence is derived. Discontinuous parse tree can be further inferred via integrating a high-performance pseudo-continuous constituency parser. Our systems are evaluated on three classical discontinuous constituency treebanks, achieving new state-of-the-art on two treebanks and showing a distinct advantage in speed.

Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to construct training instances. Then, a denoising language model is trained to restore the corrupted tokens. Existing studies have made progress by optimizing independent strategies of either ennoising or denosing. They treat training instances equally throughout the training process, with little attention on the individual contribution of those instances. To model explicit signals of instance contribution, this work proposes to estimate the complexity of restoring the original sentences from corrupted ones in language model pre-training. The estimations involve the corruption degree in the ennoising data construction process and the prediction confidence in the denoising counterpart. Experimental results on natural language understanding and reading comprehension benchmarks show that our approach improves pre-training efficiency, effectiveness, and robustness. Code is publicly available at https://github.com/cooelf/InstanceReg.

We propose to improve unsupervised neural machine translation with cross-lingual supervision (), which utilizes supervision signals from high resource language pairs to improve the translation of zero-source languages. Specifically, for training En-Ro system without parallel corpus, we can leverage the corpus from En-Fr and En-De to collectively train the translation from one language into many languages under one model. % is based on multilingual models which require no changes to the standard unsupervised NMT. Simple and effective, significantly improves the translation quality with a big margin in the benchmark unsupervised translation tasks, and even achieves comparable performance to supervised NMT. In particular, on WMT’14 -tasks achieves 37.6 and 35.18 BLEU score, which is very close to the large scale supervised setting and on WMT’16 -tasks achieves 35.09 BLEU score which is even better than the supervised Transformer baseline.

This paper describes our system (Team ID: nictrb) for participating in the WAT’21 restricted machine translation task. In our submitted system, we designed a new training approach for restricted machine translation. By sampling from the translation target, we can solve the problem that ordinary training data does not have a restricted vocabulary. With the further help of constrained decoding in the inference phase, we achieved better results than the baseline, confirming the effectiveness of our solution. In addition, we also tried the vanilla and sparse Transformer as the backbone network of the model, as well as model ensembling, which further improved the final translation performance.

Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruning-based and syntax feature-based. Experiments are conducted on the CoNLL-2005, -2009, and -2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.

In this paper, we describe our MiSS system that participated in the WMT21 news translation task. We mainly participated in the evaluation of the three translation directions of English-Chinese and Japanese-English translation tasks. In the systems submitted, we primarily considered wider networks, deeper networks, relative positional encoding, and dynamic convolutional networks in terms of model structure, while in terms of training, we investigated contrastive learning-reinforced domain adaptation, self-supervised training, and optimization objective switching training methods. According to the final evaluation results, a deeper, wider, and stronger network can improve translation performance in general, yet our data domain adaption method can improve performance even more. In addition, we found that switching to the use of our proposed objective during the finetune phase using relatively small domain-related data can effectively improve the stability of the model’s convergence and achieve better optimal performance.

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words in pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.

Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To alleviate such difficulties, previous models focus on how to incorporate these information using complex graph-based modules and additional manually labeled data, which is usually rare in real scenarios. In this paper, we design two labour-free self- and pseudo-self-supervised prediction tasks on speaker and key-utterance to implicitly model the speaker information flows, and capture salient clues in a long dialogue. Experimental results on two benchmark datasets have justified the effectiveness of our method over competitive baselines and current state-of-the-art models.

Machine reading comprehension (MRC) is a challenging NLP task for it requires to carefully deal with all linguistic granularities from word, sentence to passage. For extractive MRC, the answer span has been shown mostly determined by key evidence linguistic units, in which it is a sentence in most cases. However, we recently discovered that sentences may not be clearly defined in many languages to different extents, so that this causes so-called location unit ambiguity problem and as a result makes it difficult for the model to determine which sentence exactly contains the answer span when sentence itself has not been clearly defined at all. Taking Chinese language as a case study, we explain and analyze such a linguistic phenomenon and correspondingly propose a reader with Explicit Span-Sentence Predication to alleviate such a problem. Our proposed reader eventually helps achieve a new state-of-the-art on Chinese MRC benchmark and shows great potential in dealing with other languages.

Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results. Meanwhile, there are still several challenges for UNMT. This tutorial first introduces the background and the latest progress of UNMT. We then examine a number of challenges to UNMT and give empirical results on how well the technology currently holds up.

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e., embeddings of different levels of linguistic units or text with quite diverse lengths in a uniform vector space. We propose the training objective MiSAD that utilizes meaningful n-grams extracted from large unlabeled corpus by a simple but effective algorithm for pre-trained language models. Then we empirically verify that well designed pre-training scheme may effectively yield universal language representation, which will bring great convenience when handling multiple layers of linguistic objects in a unified way. Especially, our model achieves the highest accuracy on analogy tasks in different language levels and significantly improves the performance on downstream tasks in the GLUE benchmark and a question answering dataset.

Pre-trained language models (PrLMs) have demonstrated superior performance due to their strong ability to learn universal language representations from self-supervised pre-training. However, even with the help of the powerful PrLMs, it is still challenging to effectively capture task-related knowledge from dialogue texts which are enriched by correlations among speaker-aware utterances. In this work, we present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives: 1) utterance order restoration, which predicts the order of the permuted utterances in dialogue context; 2) sentence backbone regularization, which regularizes the model to improve the factual correctness of summarized subject-verb-object triplets. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.

Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance still lags behind traditional supervised machine translation. In unsupervised machine translation, the model seeks symmetric language similarities as a source of weak parallel signal to achieve translation. Chomsky’s Universal Grammar theory postulates that grammar is an innate form of knowledge to humans and is governed by universal principles and constraints. Therefore, in this paper, we seek to leverage such shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. Through experiments on multiple typical language pairs, we demonstrate the effectiveness of our proposed approaches.

Conversational machine reading (CMR) requires machines to communicate with humans through multi-turn interactions between two salient dialogue states of decision making and question generation processes. In open CMR settings, as the more realistic scenario, the retrieved background knowledge would be noisy, which results in severe challenges in the information transmission. Existing studies commonly train independent or pipeline systems for the two subtasks. However, those methods are trivial by using hard-label decisions to activate question generation, which eventually hinders the model performance. In this work, we propose an effective gating strategy by smoothing the two dialogue states in only one decoder and bridge decision making and question generation to provide a richer dialogue state reference. Experiments on the OR-ShARC dataset show the effectiveness of our method, which achieves new state-of-the-art results.

Aspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources and reduce the error propagation in the pipeline. However, most of the existing joint models only focus on the benefits of encoder sharing between subtasks but ignore the difference. Therefore, we propose a joint ABSA model, which not only enjoys the benefits of encoder sharing but also focuses on the difference to improve the effectiveness of the model. In detail, we introduce a dual-encoder design, in which a pair encoder especially focuses on candidate aspect-opinion pair classification, and the original encoder keeps attention on sequence labeling. Empirical results show that our proposed model shows robustness and significantly outperforms the previous state-of-the-art on four benchmark datasets.

In this paper, we present MiSS, an assistant for multi-style simultaneous translation. Our proposed translation system has five key features: highly accurate translation, simultaneous translation, translation for multiple text styles, back-translation for translation quality evaluation, and grammatical error correction. With this system, we aim to provide a complete translation experience for machine translation users. Our design goals are high translation accuracy, real-time translation, flexibility, and measurable translation quality. Compared with the free commercial translation systems commonly used, our translation assistance system regards the machine translation application as a more complete and fully-featured tool for users. By incorporating additional features and giving the user better control over their experience, we improve translation efficiency and performance. Additionally, our assistant system combines machine translation, grammatical error correction, and interactive edits, and uses a crowdsourcing mode to collect more data for further training to improve both the machine translation and grammatical error correction models. A short video demonstrating our system is available at https://www.youtube.com/watch?v=ZGCo7KtRKd8.

This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.

In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation directions of three language pairs: English-Chinese, English-Polish on supervised machine translation track, German-Upper Sorbian on low-resource and unsupervised machine translation tracks. Based on different conditions of language pairs, we have experimented with diverse neural machine translation (NMT) techniques: document-enhanced NMT, XLM pre-trained language model enhanced NMT, bidirectional translation as a pre-training, reference language based UNMT, data-dependent gaussian prior objective, and BT-BLEU collaborative filtering self-training. We also used the TF-IDF algorithm to filter the training set to obtain a domain more similar set with the test set for finetuning. In our submissions, the primary systems won the first place on English to Chinese, Polish to English, and German to Upper Sorbian translation directions.

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the relationships between predicates and arguments and the correlations between arguments at most, while the correlations between predicates have been neglected for a long time. High-order features and structure learning were very common in modeling such correlations before the neural network era. In this paper, we introduce a high-order graph structure for the neural semantic role labeling model, which enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models and further boost our baseline to achieve new state-of-the-art results.

Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used pivot language in the absence of a source language to target language parallel corpus. The rise of unsupervised neural machine translation (UNMT) almost completely relieves the parallel corpus curse, though UNMT is still subject to unsatisfactory performance due to the vagueness of the clues available for its core back-translation training. Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community.

Both syntactic and semantic structures are key linguistic contextual clues, in which parsing the latter has been well shown beneficial from parsing the former. However, few works ever made an attempt to let semantic parsing help syntactic parsing. As linguistic representation formalisms, both syntax and semantics may be represented in either span (constituent/phrase) or dependency, on both of which joint learning was also seldom explored. In this paper, we propose a novel joint model of syntactic and semantic parsing on both span and dependency representations, which incorporates syntactic information effectively in the encoder of neural network and benefits from two representation formalisms in a uniform way. The experiments show that semantics and syntax can benefit each other by optimizing joint objectives. Our single model achieves new state-of-the-art or competitive results on both span and dependency semantic parsing on Propbank benchmarks and both dependency and constituent syntactic parsing on Penn Treebank.

In this paper, we present Linguistics Informed Multi-Task BERT (LIMIT-BERT) for learning language representations across multiple linguistics tasks by Multi-Task Learning. LIMIT-BERT includes five key linguistics tasks: Part-Of-Speech (POS) tags, constituent and dependency syntactic parsing, span and dependency semantic role labeling (SRL). Different from recent Multi-Task Deep Neural Networks (MT-DNN), our LIMIT-BERT is fully linguistics motivated and thus is capable of adopting an improved masked training objective according to syntactic and semantic constituents. Besides, LIMIT-BERT takes a semi-supervised learning strategy to offer the same large amount of linguistics task data as that for the language model training. As a result, LIMIT-BERT not only improves linguistics tasks performance but also benefits from a regularization effect and linguistics information that leads to more general representations to help adapt to new tasks and domains. LIMIT-BERT outperforms the strong baseline Whole Word Masking BERT on both dependency and constituent syntactic/semantic parsing, GLUE benchmark, and SNLI task. Our practice on the proposed LIMIT-BERT also enables us to release a well pre-trained model for multi-purpose of natural language processing tasks once for all.

In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outermost entities and a graph module for all the entities located in inner layers. Bidirectional LSTM (BiLSTM) and graph convolutional network (GCN) are adopted to jointly learn flat entities and their inner dependencies. Different from previous models, which only consider the unidirectional delivery of information from innermost layers to outer ones (or outside-to-inside), our model effectively captures the bidirectional interaction between them. We first use the entities recognized by the flat NER module to construct an entity graph, which is fed to the next graph module. The richer representation learned from graph module carries the dependencies of inner entities and can be exploited to improve outermost entity predictions. Experimental results on three standard nested NER datasets demonstrate that our BiFlaG outperforms previous state-of-the-art models.

Taking greedy decoding algorithm as it should be, this work focuses on further strengthening the model itself for Chinese word segmentation (CWS), which results in an even more fast and more accurate CWS model. Our model consists of an attention only stacked encoder and a light enough decoder for the greedy segmentation plus two highway connections for smoother training, in which the encoder is composed of a newly proposed Transformer variant, Gaussian-masked Directional (GD) Transformer, and a biaffine attention scorer. With the effective encoder design, our model only needs to take unigram features for scoring. Our model is evaluated on SIGHAN Bakeoff benchmark datasets. The experimental results show that with the highest segmentation speed, the proposed model achieves new state-of-the-art or comparable performance against strong baselines in terms of strict closed test setting.

Deep neural network models have helped named entity recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings.We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and then refine these coarse-grained annotations through neural networks. Extensive experiments on two CoNLL benchmark NER datasets (CoNLL-2003 English dataset and CoNLL-2002 Spanish dataset) demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.

Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.

Semantic role labeling (SRL) is a task to recognize all the predicate-argument pairs of a sentence, which has been in a performance improvement bottleneck after a series of latest works were presented. This paper proposes a novel syntax-agnostic SRL model enhanced by the proposed associated memory network (AMN), which makes use of inter-sentence attention of label-known associated sentences as a kind of memory to further enhance dependency-based SRL. In detail, we use sentences and their labels from train dataset as an associated memory cue to help label the target sentence. Furthermore, we compare several associated sentences selecting strategies and label merging methods in AMN to find and utilize the label of associated sentences while attending them. By leveraging the attentive memory from known training data, Our full model reaches state-of-the-art on CoNLL-2009 benchmark datasets for syntax-agnostic setting, showing a new effective research line of SRL enhancement other than exploiting external resources such as well pre-trained language models.

This paper describes our SJTU-NICT’s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Our system uses a graph-based approach to model a variety of semantic graph parsing tasks. Our main contributions in the submitted system are summarized as follows: 1. Our model is fully end-to-end and is capable of being trained only on the given training set which does not rely on any other extra training source including the companion data provided by the organizer; 2. We extend our graph pruning algorithm to a variety of semantic graphs, solving the problem of excessive semantic graph search space; 3. We introduce multi-task learning for multiple objectives within the same framework. The evaluation results show that our system achieved second place in the overall F₁ score and achieved the best F₁ score on the DM framework.

This paper describes the system of our team SJTU for our participation in the CoNLL 2019 Shared Task: Cross-Framework Meaning Representation Parsing. The goal of the task is to advance data-driven parsing into graph-structured representations of sentence meaning. This task includes five meaning representation frameworks: DM, PSD, EDS, UCCA, and AMR. These frameworks have different properties and structures. To tackle all the frameworks in one model, it is needed to find out the commonality of them. In our work, we define a set of the transition actions to once-for-all tackle all the frameworks and train a transition-based model to parse the meaning representation. The adopted multi-task model also can allow learning for one framework to benefit the others. In the final official evaluation of the shared task, our system achieves 42% F1 unified MRP metric score.

Recently, semantic role labeling (SRL) has earned a series of success with even higher performance improvements, which can be mainly attributed to syntactic integration and enhanced word representation. However, most of these efforts focus on English, while SRL on multiple languages more than English has received relatively little attention so that is kept underdevelopment. Thus this paper intends to fill the gap on multilingual SRL with special focus on the impact of syntax and contextualized word representation. Unlike existing work, we propose a novel method guided by syntactic rule to prune arguments, which enables us to integrate syntax into multilingual SRL model simply and effectively. We present a unified SRL model designed for multiple languages together with the proposed uniform syntax enhancement. Our model achieves new state-of-the-art results on the CoNLL-2009 benchmarks of all seven languages. Besides, we pose a discussion on the syntactic role among different languages and verify the effectiveness of deep enhanced representation for multilingual SRL.

Pinyin-to-character (P2C) conversion is the core component of pinyin-based Chinese input method engine (IME). However, the conversion is seriously compromised by the ambiguities of Chinese characters corresponding to pinyin as well as the predefined fixed vocabularies. To alleviate such inconveniences, we propose a neural P2C conversion model augmented by an online updated vocabulary with a sampling mechanism to support open vocabulary learning during IME working. Our experiments show that the proposed method outperforms commercial IMEs and state-of-the-art traditional models on standard corpus and true inputting history dataset in terms of multiple metrics and thus the online updated vocabulary indeed helps our IME effectively follows user inputting behavior.

Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism representing rich contextual syntactic and even semantic meanings. This paper makes the first attempt to formulate a simplified HPSG by integrating constituent and dependency formal representations into head-driven phrase structure. Then two parsing algorithms are respectively proposed for two converted tree representations, division span and joint span. As HPSG encodes both constituent and dependency structure information, the proposed HPSG parsers may be regarded as a sort of joint decoder for both types of structures and thus are evaluated in terms of extracted or converted constituent and dependency parsing trees. Our parser achieves new state-of-the-art performance for both parsing tasks on Penn Treebank (PTB) and Chinese Penn Treebank, verifying the effectiveness of joint learning constituent and dependency structures. In details, we report 95.84 F1 of constituent parsing and 97.00% UAS of dependency parsing on PTB.

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes. We hypothesize that the diversity in segmentations may affect the NMT performance. To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training. We propose two methods: 1) lattice positional encoding and 2) lattice-aware self-attention. These two methods can be used together and show complementary to each other to further improve translation performance. Experiment results show superiorities of lattice-based encoders in word-level and subword-level representations over conventional Transformer encoder.

This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined vocabulary. We introduce a neural network architecture for the concerned task and empirically study various neural network models to build the representations in latent space for words and phrases. The evaluated models include convolutional neural network, long-short term memory network, gated recurrent unit and recurrent convolutional neural network. We also explore different embedding methods, including word embedding and sense embedding for better performance.

Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics.

Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs. Thus, properly representing the text is very crucial to this task. In this paper, we propose a model augmented with different grained text representations, including character, subword, word, sentence, and sentence pair levels. The proposed deeper model is evaluated on the benchmark treebank and achieves state-of-the-art accuracy with greater than 48% in 11-way and F1 score greater than 50% in 4-way classifications for the first time according to our best knowledge.

Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic unit. In addition, with a simple concatenation of character and word embedding, previous models actually give suboptimal solution. In this paper, we propose to use subword rather than character for word embedding enhancement. We also empirically explore different augmentation strategies on subword-augmented embedding to enhance the cloze-style reading comprehension model (reader). In detail, we present a reader that uses subword-level representation to augment word embedding with a short list to handle rare words effectively. A thorough examination is conducted to evaluate the comprehensive performance and generalization ability of the proposed reader. Experimental results show that the proposed approach helps the reader significantly outperform the state-of-the-art baselines on various public datasets.

Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the semantic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models.

This paper presents a sequence to sequence (seq2seq) dependency parser by directly predicting the relative position of head for each given word, which therefore results in a truly end-to-end seq2seq dependency parser for the first time. Enjoying the advantage of seq2seq modeling, we enrich a series of embedding enhancement, including firstly introduced subword and node2vec augmentation. Meanwhile, we propose a beam search decoder with tree constraint and subroot decomposition over the sequence to furthermore enhance our seq2seq parser. Our parser is evaluated on benchmark treebanks, being on par with the state-of-the-art parsers by achieving 94.11% UAS on PTB and 88.78% UAS on CTB, respectively.

Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus.

Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.

Semantic role labeling (SRL) aims to recognize the predicate-argument structure of a sentence. Syntactic information has been paid a great attention over the role of enhancing SRL. However, the latest advance shows that syntax would not be so important for SRL with the emerging much smaller gap between syntax-aware and syntax-agnostic SRL. To comprehensively explore the role of syntax for SRL task, we extend existing models and propose a unified framework to investigate more effective and more diverse ways of incorporating syntax into sequential neural networks. Exploring the effect of syntactic input quality on SRL performance, we confirm that high-quality syntactic parse could still effectively enhance syntactically-driven SRL. Using empirically optimized integration strategy, we even enlarge the gap between syntax-aware and syntax-agnostic SRL. Our framework achieves state-of-the-art results on CoNLL-2009 benchmarks both for English and Chinese, substantially outperforming all previous models.

Chinese pinyin input method engine (IME) converts pinyin into character so that Chinese characters can be conveniently inputted into computer through common keyboard. IMEs work relying on its core component, pinyin-to-character conversion (P2C). Usually Chinese IMEs simply predict a list of character sequences for user choice only according to user pinyin input at each turn. However, Chinese inputting is a multi-turn online procedure, which can be supposed to be exploited for further user experience promoting. This paper thus for the first time introduces a sequence-to-sequence model with gated-attention mechanism for the core task in IMEs. The proposed neural P2C model is learned by encoding previous input utterance as extra context to enable our IME capable of predicting character sequence with incomplete pinyin input. Our model is evaluated in different benchmark datasets showing great user experience improvement compared to traditional models, which demonstrates the first engineering practice of building Chinese aided IME.

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently no matter how similar they are. However, this might be inefficient since some partial hypotheses can contain only local differences that will not influence future predictions. In this work, we introduce recombination in NMT decoding based on the concept of the “equivalence” of partial hypotheses. Heuristically, we use a simple n-gram suffix based equivalence function and adapt it into beam search decoding. Through experiments on large-scale Chinese-to-English and English-to-Germen translation tasks, we show that the proposed method can obtain similar translation quality with a smaller beam size, making NMT decoding more efficient.

Semantic role labeling (SRL) is dedicated to recognizing the predicate-argument structure of a sentence. Previous studies have shown syntactic information has a remarkable contribution to SRL performance. However, such perception was challenged by a few recent neural SRL models which give impressive performance without a syntactic backbone. This paper intends to quantify the importance of syntactic information to dependency SRL in deep learning framework. We propose an enhanced argument labeling model companying with an extended korder argument pruning algorithm for effectively exploiting syntactic information. Our model achieves state-of-the-art results on the CoNLL-2008, 2009 benchmarks for both English and Chinese, showing the quantitative significance of syntax to neural SRL together with a thorough empirical survey over existing models.

Comments of online articles provide extended views and improve user engagement. Automatically making comments thus become a valuable functionality for online forums, intelligent chatbots, etc. This paper proposes the new task of automatic article commenting, and introduces a large-scale Chinese dataset with millions of real comments and a human-annotated subset characterizing the comments’ varying quality. Incorporating the human bias of comment quality, we further develop automatic metrics that generalize a broad set of popular reference-based metrics and exhibit greatly improved correlations with human evaluations.

Chinese pinyin input method engine (IME) lets user conveniently input Chinese into a computer by typing pinyin through the common keyboard. In addition to offering high conversion quality, modern pinyin IME is supposed to aid user input with extended association function. However, existing solutions for such functions are roughly based on oversimplified matching algorithms at word-level, whose resulting products provide limited extension associated with user inputs. This work presents the Moon IME, a pinyin IME that integrates the attention-based neural machine translation (NMT) model and Information Retrieval (IR) to offer amusive and customizable association ability. The released IME is implemented on Windows via text services framework.

This paper describes the system of team LeisureX in the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system predicts the part-of-speech tag and dependency tree jointly. For the basic tasks, including tokenization, lemmatization and morphology prediction, we employ the official baseline model (UDPipe). To train the low-resource languages, we adopt a sampling method based on other richresource languages. Our system achieves a macro-average of 68.31% LAS F1 score, with an improvement of 2.51% compared with the UDPipe.

This paper describes the system of our team Phoenix for participating CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Given the annotated gold standard data in CoNLL-U format, we train the tokenizer, tagger and parser separately for each treebank based on an open source pipeline tool UDPipe. Our system reads the plain texts for input, performs the pre-processing steps (tokenization, lemmas, morphology) and finally outputs the syntactic dependencies. For the low-resource languages with no training data, we use cross-lingual techniques to build models with some close languages instead. In the official evaluation, our system achieves the macro-averaged scores of 65.61%, 52.26%, 55.71% for LAS, MLAS and BLEX respectively.

Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark.

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are computationally inefficient. In this paper, we propose a greedy neural word segmenter with balanced word and character embedding inputs to alleviate the existing drawbacks. Our segmenter is truly end-to-end, capable of performing segmentation much faster and even more accurate than state-of-the-art neural models on Chinese benchmark datasets.

This paper describes the system for our participation in the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In this work, we design a system based on UDPipe1 for universal dependency parsing, where multilingual transition-based models are trained for different treebanks. Our system directly takes raw texts as input, performing several intermediate steps like tokenizing and tagging, and finally generates the corresponding dependency trees. For the special surprise languages for this task, we adopt a delexicalized strategy and predict basing on transfer learning from other related languages. In the final evaluation of the shared task, our system achieves a result of 66.53% in macro-averaged LAS F1-score.

For the task of implicit discourse relation recognition, traditional models utilizing manual features can suffer from data sparsity problem. Neural models provide a solution with distributed representations, which could encode the latent semantic information, and are suitable for recognizing semantic relations between argument pairs. However, conventional vector representations usually adopt embeddings at the word level and cannot well handle the rare word problem without carefully considering morphological information at character level. Moreover, embeddings are assigned to individual words independently, which lacks of the crucial contextual information. This paper proposes a neural model utilizing context-aware character-enhanced embeddings to alleviate the drawbacks of the current word level representation. Our experiments show that the enhanced embeddings work well and the proposed model obtains state-of-the-art results.

Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains of the original corpus can indeed enhance SMT performance directly. A series of SMT adaptation methods have been proposed to select these similar-domain data, and most of them focus on sentence selection. In comparison, phrase is a smaller and more fine grained unit for data selection, therefore we propose a straightforward and efficient connecting phrase based adaptation method, which is applied to both bilingual phrase pair and monolingual n-gram adaptation. The proposed method is evaluated on IWSLT/NIST data sets, and the results show that phrase based SMT performances are significantly improved (up to +1.6 in comparison with phrase based SMT baseline system and +0.9 in comparison with existing methods).

This paper presents some novel results on Chinese spell checking. In this paper, a concise algorithm based on minimized-path segmentation is proposed to reduce the cost and suit the needs of current Chinese input systems. The proposed algorithm is actually derived from a simple assumption that spelling errors often make the number of segments larger. The experimental results are quite positive and implicitly verify the effectiveness of the proposed assumption. Finally, all approaches work together to output a result much better than the baseline with 12% performance improvement.

We investigate the impact of input data scale in corpus-based learning using a study style of Zipf’s law. In our research, Chinese word segmentation is chosen as the study case and a series of experiments are specially conducted for it, in which two types of segmentation techniques, statistical learning and rule-based methods, are examined. The empirical results show that a linear performance improvement in statistical learning requires an exponential increasing of training corpus size at least. As for the rule-based method, an approximate negative inverse relationship between the performance and the size of the input lexicon can be observed.