Most text-to-SQL models, even though based on the same grammar decoder, generate the SQL structure first and then fill in the SQL slots with the correct schema items. This second step depends on schema linking: aligning the entity references in the question with the schema columns or tables. This is generally approached via Exact Match based Schema Linking (EMSL) within a neural network-based schema linking module. EMSL has become standard in text-to-SQL: many state-of-the-art models employ EMSL, with performance dropping significantly when the EMSL component is removed. In this work, however, we show that EMSL reduces robustness, rendering models vulnerable to synonym substitution and typos. Instead of relying on EMSL to make up for deficiencies in question-schema encoding, we show that using a pre-trained language model as an encoder can improve performance without using EMSL, giving a more robust model. We also study the design choice of the schema linking module, finding that a suitable design benefits performance and interoperability. Finally, based on the above study of schema linking, we introduce the grammar linking to help model align grammar references in the question with the SQL keywords.

Collaboration increasingly happens online. This is especially true for large groups working on global tasks, with collaborators all around the globe. The size and distributed nature of such groups makes decision-making challenging. This paper proposes a set of dialog acts for the study of decision-making mechanisms in such groups, and provides a new annotated dataset based on real-world data from the public mail-archives of one such organisation – the Internet Engineering Task Force (IETF). We provide an initial data analysis showing that this dataset can be used to better understand decision-making in such organisations. Finally, we experiment with a preliminary transformer-based dialog act tagging model.

This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the “low resource” languages.

This paper presents our work on the SemEval-2023 Task 10 Explainable Detection of Online Sexism (EDOS) using lexicon-based models. Our approach consists of three main steps: lexicon construction based on Pointwise Mutual Information (PMI) and Shapley value, lexicon augmentation using an unannotated corpus and Large Language Models (LLMs), and, lastly, lexical incorporation for Bag-of-Word (BoW) logistic regression and fine-tuning LLMs. Our results demonstrate that our Shapley approach effectively produces a high-quality lexicon. We also show that by simply counting the presence of certain words in our lexicons and comparing the count can outperform a BoW logistic regression in task B/C and fine-tuning BERT in task C. In the end, our classifier achieved F1-scores of 53.34\% and 27.31\% on the official blind test sets for tasks B and C, respectively. We, additionally, provide in-depth analysis highlighting model limitation and bias. We also present our attempts to understand the model’s behaviour based on our constructed lexicons. Our code and the resulting lexicons are open-sourced in our GitHub repository https://github.com/SirBadr/SemEval2022-Task10.

We study the influence of different activation functions in the output layer of pre-trained transformer models for soft and hard label prediction in the learning with disagreement task. In this task, the goal is to quantify the amount of disagreement via predicting soft labels. To predict the soft labels, we use BERT-based preprocessors and encoders and vary the activation function used in the output layer, while keeping other parameters constant. The soft labels are then used for the hard label prediction. The activation functions considered are sigmoid as well as a step-function that is added to the model post-training and a sinusoidal activation function, which is introduced for the first time in this paper.

Recent works on linear text segmentation have shown new state-of-the-art results nearly every year. Most times, however, these recent advances include a variety of different elements which makes it difficult to evaluate which individual components of the proposed methods bring about improvements for the task and, more generally, what actually works for linear text segmentation. Moreover, evaluating text segmentation is notoriously difficult and the use of a metric such as Pk, which is widely used in existing literature, presents specific problems that complicates a fair comparison between segmentation models. In this work, then, we draw from a number of existing works to assess which is the state-of-the-art in linear text segmentation, investigating what architectures and features work best for the task. For doing so, we present three models representative of a variety of approaches, we compare them to existing methods and we inspect elements composing them, so as to give a more complete picture of which technique is more successful and why that might be the case. At the same time, we highlight a specific feature of Pk which can bias the results and we report our results using different settings, so as to give future literature a more comprehensive set of baseline results for future developments. We then hope that this work can serve as a solid foundation to foster research in the area, overcoming task-specific difficulties such as evaluation setting and providing new state-of-the-art results.

Dementia is associated with language disorders which impede communication. Here, we automatically learn linguistic disorder patterns by making use of a moderately-sized pre-trained language model and forcing it to focus on reformulated natural language processing (NLP) tasks and associated linguistic patterns. Our experiments show that NLP tasks that encapsulate contextual information and enhance the gradient signal with linguistic patterns benefit performance. We then use the probability estimates from the best model to construct digital linguistic markers measuring the overall quality in communication and the intensity of a variety of language disorders. We investigate how the digital markers characterize dementia speech from a longitudinal perspective. We find that our proposed communication marker is able to robustly and reliably characterize the language of people with dementia, outperforming existing linguistic approaches; and shows external validity via significant correlation with clinical markers of behaviour. Finally, our proposed linguistic disorder markers provide useful insights into gradual language impairment associated with disease progression.

Social science and psycholinguistic research have shown that power and status affect how people use language in a range of domains. Here, we investigate a similar question in a large, distributed, consensus-driven community with little traditional power hierarchy – the Internet Engineering Task Force (IETF), a collaborative organisation that designs internet standards. Our analysis based on lexical categories (LIWC) and BERT, shows that participants’ levels of influence can be predicted from their email text, and identify key linguistic differences (e.g., certain LIWC categories, such as “WE” are positively correlated with high-influence). We also identify the differences in language use for the same person before and after becoming influential.

User-generated content is full of misspellings. Rather than being just random noise, we hypothesise that many misspellings contain hidden semantics that can be leveraged for language understanding tasks. This paper presents a fine-grained annotated corpus of misspelling in Thai, together with an analysis of misspelling intention and its possible semantics to get a better understanding of the misspelling patterns observed in the corpus. In addition, we introduce two approaches to incorporate the semantics of misspelling: Misspelling Average Embedding (MAE) and Misspelling Semantic Tokens (MST). Experiments on a sentiment analysis task confirm our overall hypothesis: additional semantics from misspelling can boost the micro F1 score up to 0.4-2%, while blindly normalising misspelling is harmful and suboptimal.

In text-to-SQL tasks — as in much of NLP — compositional generalization is a major challenge: neural networks struggle with compositional generalization where training and test distributions differ. However, most recent attempts to improve this are based on word-level synthetic data or specific dataset splits to generate compositional biases. In this work, we propose a clause-level compositional example generation method. We first split the sentences in the Spider text-to-SQL dataset into sub-sentences, annotating each sub-sentence with its corresponding SQL clause, resulting in a new dataset Spider-SS. We then construct a further dataset, Spider-CG, by composing Spider-SS sub-sentences in different combinations, to test the ability of models to generalize compositionally. Experiments show that existing models suffer significant performance degradation when evaluated on Spider-CG, even though every sub-sentence is seen during training. To deal with this problem, we modify a number of state-of-the-art models to train on the segmented data of Spider-SS, and we show that this method improves the generalization performance.

In light of unprecedented increases in the popularity of the internet and social media, comment moderation has never been a more relevant task. Semi-automated comment moderation systems greatly aid human moderators by either automatically classifying the examples or allowing the moderators to prioritize which comments to consider first. However, the concept of inappropriate content is often subjective, and such content can be conveyed in many subtle and indirect ways. In this work, we propose CoRAL – a language and culturally aware Croatian Abusive dataset covering phenomena of implicitness and reliance on local and global context. We show experimentally that current models degrade when comments are not explicit and further degrade when language skill and context knowledge are required to interpret the comment.

There is a global trend for responsible investing and the need for developing automated methods for analyzing and Environmental, Social and Governance (ESG) related elements in financial texts is raising. In this work we propose a solution to the FinSim4-ESG task, consisting of binary classification of sentences into sustainable or unsustainable. We propose a novel knowledge-based latent heterogeneous representation that is based on knowledge from taxonomies and knowledge graphs and multiple contemporary document representations. We hypothesize that an approach based on a combination of knowledge and document representations can introduce significant improvement over conventional document representation approaches. We consider ensembles on classifier as well on representation level late-fusion and early fusion. The proposed approaches achieve competitive accuracy of 89 and are 5.85 behind the best achieved score.

We describe initial work into analysing the language used around environmental, social and governance (ESG) issues in UK company annual reports. We collect a dataset of annual reports from UK FTSE350 companies over the years 2012-2019; separately, we define a categorized list of core ESG terms (single words and multi-word expressions) by combining existing lists with manual annotation. We then show that this list can be used to analyse the changes in ESG language in the dataset over time, via a combination of language modelling and distributional modelling via contextual word embeddings. Initial findings show that while ESG discussion in annual reports is becoming significantly more likely over time, the increase varies with category and with individual terms, and that some terms show noticeable changes in usage.

The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be a semantically matching word vector. The reverse dictionary is useful in practical applications such as solving the tip-of-the-tongue problem, helping new language learners, etc. In this paper, we evaluate the effect of a Transformer-based model with cross-lingual zero-shot learning to improve the reverse dictionary performance. Our experiments are conducted in five languages in the CODWOE dataset, including English, French, Italian, Spanish, and Russian. Even if we did not achieve a good ranking in the CODWOE competition, we show that our work partially improves the current baseline from the organizers with a hypothesis on the impact of LSTM in monolingual, multilingual, and zero-shot learning. All the codes are available at https://github.com/honghanhh/codwoe2021.

Moderation of reader comments is a significant problem for online news platforms. Here, we experiment with models for automatic moderation, using a dataset of comments from a popular Croatian newspaper. Our analysis shows that while comments that violate the moderation rules mostly share common linguistic and thematic features, their content varies across the different sections of the newspaper. We therefore make our models topic-aware, incorporating semantic features from a topic model into the classification decision. Our results show that topic information improves the performance of the model, increases its confidence in correct outputs, and helps us understand the model’s outputs.

Alzheimer’s Disease (AD) is associated with many characteristic changes, not only in an individual’s language but also in the interactive patterns observed in dialogue. The most indicative changes of this latter kind tend to be associated with relatively rare dialogue acts (DAs), such as those involved in clarification exchanges and responses to particular kinds of questions. However, most existing work in DA tagging focuses on improving average performance, effectively prioritizing more frequent classes; it thus gives a poor performance on these rarer classes and is not suited for application to AD analysis. In this paper, we investigate tagging specifically for rare class DAs, using a hierarchical BiLSTM model with various ways of incorporating information from previous utterances and DA tags in context. We show that this can give good performance for rare DA classes on both the general Switchboard corpus (SwDA) and an AD-specific conversational dataset, the Carolinas Conversation Collection (CCC); and that the tagger outputs then contribute useful information for distinguishing patients with and without AD

This work revisits the task of detecting decision-related utterances in multi-party dialogue. We explore performance of a traditional approach and a deep learning-based approach based on transformer language models, with the latter providing modest improvements. We then analyze topic bias in the models using topic information obtained by manual annotation. Our finding is that when detecting some types of decisions in our data, models rely more on topic specific words that decisions are about rather than on words that more generally indicate decision making. We further explore this by removing topic information from the train data. We show that this resolves the bias issues to an extent and, surprisingly, sometimes even boosts performance.

Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts in the text descriptions; (2) removing the need of nested subqueries and set operators; and (3) making the schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benchmark that contains complex and nested SQL queries, we demonstrate that NatSQL outperforms other IRs, and significantly improves the performance of several previous SOTA models. Furthermore, for existing models that do not support executable SQL generation, NatSQL easily enables them to generate executable SQL queries, and achieves the new state-of-the-art execution accuracy.

Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matching between words in natural language (NL) questions and tokens in table schemas, which may render the models vulnerable to attacks that break the schema linking mechanism. In this work, we investigate the robustness of text-to-SQL models to synonym substitution. In particular, we introduce Spider-Syn, a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-Syn are modified from Spider, by replacing their schema-related words with manually selected synonyms that reflect real-world question paraphrases. We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case attacks. Finally, we present two categories of approaches to improve the model robustness. The first category of approaches utilizes additional synonym annotations for table schemas by modifying the model input, while the second category is based on adversarial training. We demonstrate that both categories of approaches significantly outperform their counterparts without the defense, and the first category of approaches are more effective.

We present a conversational management act (CMA) annotation schema for one-to-one tutorial dialogue sessions where a tutor uses an analogy to teach a student a concept. CMAs are more fine-grained sub-utterance acts compared to traditional dialogue act mark-up. The schema achieves an inter-annotator agreement (IAA) Cohen Kappa score of at least 0.66 across all 10 classes. We annotate a corpus of analogical episodes with the schema and develop statistical sequence models from the corpus which predict tutor content related decisions, in terms of the selection of the analogical component (AC) and tutor conversational management act (TCMA) to deploy at the current utterance, given the student’s behaviour. CRF sequence classifiers perform well on AC selection and robustly on TCMA selection, achieving respective accuracies of 61.9% and 56.3% on a cross-validation experiment over the corpus.

We present a system for zero-shot cross-lingual offensive language and hate speech classification. The system was trained on English datasets and tested on a task of detecting hate speech and offensive social media content in a number of languages without any additional training. Experiments show an impressive ability of both models to generalize from English to other languages. There is however an expected gap in performance between the tested cross-lingual models and the monolingual models. The best performing model (offensive content classifier) is available online as a REST API.

This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program. The collected resources were offered to participants of a hackathon organized as part of the EACL Hackashop on News Media Content Analysis and Automated Report Generation in February 2021. The hackathon had six participating teams who addressed different challenges, either from the list of proposed challenges or their own news-industry-related tasks. This paper goes beyond the scope of the hackathon, as it brings together in a coherent and compact form most of the resources developed, collected and released by the EMBEDDIA project. Moreover, it constitutes a handy source for news media industry and researchers in the fields of Natural Language Processing and Social Science.

Recently, there has been significant progress in studying neural networks for translating text descriptions into SQL queries under the zero-shot cross-domain setting. Despite achieving good performance on some public benchmarks, we observe that existing text-to-SQL models do not generalize when facing domain knowledge that does not frequently appear in the training data, which may render the worse prediction performance for unseen domains. In this work, we investigate the robustness of text-to-SQL models when the questions require rarely observed domain knowledge. In particular, we define five types of domain knowledge and introduce Spider-DK (DK is the abbreviation of domain knowledge), a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-DK are selected from Spider, and we modify some samples by adding domain knowledge that reflects real-world question paraphrases. We demonstrate that the prediction accuracy dramatically drops on samples that require such domain knowledge, even if the domain knowledge appears in the training set, and the model provides the correct predictions for related training samples.

WikiSQL and Spider, the large-scale cross-domain text-to-SQL datasets, have attracted much attention from the research community. The leaderboards of WikiSQL and Spider show that many researchers propose their models trying to solve the text-to-SQL problem. This paper first divides the top models in these two leaderboards into two paradigms. We then present details not mentioned in their original paper by evaluating the key components, including schema linking, pretrained word embeddings, and reasoning assistance modules. Based on the analysis of these models, we want to promote understanding of the text-to-SQL field and find out some interesting future works, for example, it is worth studying the text-to-SQL problem in an environment where it is more challenging to build schema linking and also worth studying combing the advantage of each model toward text-to-SQL.

We describe a set of experiments for building a temporal mental health dynamics system. We utilise a pre-existing methodology for distant- supervision of mental health data mining from social media platforms and deploy the system during the global COVID-19 pandemic as a case study. Despite the challenging nature of the task, we produce encouraging results, both explicit to the global pandemic and implicit to a global phenomenon, Christmas Depres- sion, supported by the literature. We propose a methodology for providing insight into tem- poral mental health dynamics to be utilised for strategic decision-making.

We study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Moreover, in relevant contexts we observe a discourse coherence effect that uniformly raises acceptability. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The bidirectional models show very promising results, with the best model achieving a new state-of-the-art for unsupervised acceptability prediction. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modeling of text and discourse.

State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists. Standard tasks and datasets for intrinsic evaluation of embeddings are based on judgements of similarity, but ignore context; standard tasks for word sense disambiguation take account of context but do not provide continuous measures of meaning similarity. This paper describes an effort to build a new dataset, CoSimLex, intended to fill this gap. Building on the standard pairwise similarity task of SimLex-999, it provides context-dependent similarity measures; covers not only discrete differences in word sense but more subtle, graded changes in meaning; and covers not only a well-resourced language (English) but a number of less-resourced languages. We define the task and evaluation metrics, outline the dataset collection methodology, and describe the status of the dataset so far.

This paper presents the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish. We received 15 submissions and 11 system description papers. A new dataset (CoSimLex) was created for evaluation in this task: it contains pairs of words, each annotated within two different contexts. Systems beat the baselines by significant margins, but few did well in more than one language or subtask. Almost every system employed a Transformer model, but with many variations in the details: WordNet sense embeddings, translation of contexts, TF-IDF weightings, and the automatic creation of datasets for fine-tuning were all used to good effect.

This paper discusses the problem of incongruent headlines: those which do not accurately represent the information contained in the article with which they occur. We emphasise that this phenomenon should be considered separately from recognised problematic headline types such as clickbait and sensationalism, arguing that existing natural language processing (NLP) methods applied to these related concepts are not appropriate for the automatic detection of headline incongruence, as an analysis beyond stylistic traits is necessary. We therefore suggest a number of alternative methodologies that may be appropriate to the task at hand as a foundation for future work in this area. In addition, we provide an analysis of existing data sets which are related to this work, and motivate the need for a novel data set in this domain.