COLING 2020 Papers

Text representation plays a vital role in retrieval-based question answering, especially in the legal domain where documents are usually long and complicated. The better the question and the legal documents are represented, the more accurate they are matched. In this paper, we focus on the task of answering legal questions at the article level. Given a legal question, the goal is to retrieve all the correct and valid legal articles, that can be used as the basic to answer the question. We present a retrieval-based model for the task by learning neural attentive text representation. Our text representation method first leverages convolutional neural networks to extract important information in a question and legal articles. Attention mechanisms are then used to represent the question and articles and select appropriate information to align them in a matching process. Experimental results on an annotated corpus consisting of 5,922 Vietnamese legal questions show that our model outperforms state-of-the-art retrieval-based methods for question answering by large margins in terms of both recall and NDCG.

Deep question generation (DQG) aims to generate complex questions through reasoning over multiple documents. The task is challenging and underexplored. Existing methods mainly focus on enhancing document representations, with little attention paid to the answer information, which may result in the generated question not matching the answer type and being answerirrelevant. In this paper, we propose an Answer-driven Deep Question Generation (ADDQG) model based on the encoder-decoder framework. The model makes better use of the target answer as a guidance to facilitate question generation. First, we propose an answer-aware initialization module with a gated connection layer which introduces both document and answer information to the decoder, thus helping to guide the choice of answer-focused question words. Then a semantic-rich fusion attention mechanism is designed to support the decoding process, which integrates the answer with the document representations to promote the proper handling of answer information during generation. Moreover, reinforcement learning is applied to integrate both syntactic and semantic metrics as the reward to enhance the training of the ADDQG. Extensive experiments on the HotpotQA dataset show that ADDQG outperforms state-of-the-art models in both automatic and human evaluations.

In this paper, we introduce Annobot: a platform for annotating and creating datasets through conversation with a chatbot. This natural form of interaction has allowed us to create a more accessible and flexible interface, especially for mobile devices. Our solution has a wide range of applications such as data labelling for binary, multi-class/label classification tasks, preparing data for regression problems, or creating sets for issues such as machine translation, question answering or text summarization. Additional features include pre-annotation, active sampling, online learning and real-time inter-annotator agreement. The system is integrated with the popular messaging platform: Facebook Messanger. Usability experiment showed the advantages of the proposed platform compared to other labelling tools. The source code of Annobot is available under the GNU LGPL license at https://github.com/rafalposwiata/annobot.

Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. However, most of the prior work on this topic has focused on high resource languages. In this paper, we evaluate cross-lingual approaches for low resource languages, especially in the context of morphologically rich Indian languages. We test our model on six languages from two different families and develop linguistic insights into each model’s performance.

Analogy is assumed to be the cognitive mechanism speakers resort to in order to inflect an unknown form of a lexeme based on knowledge of other words in a language. In this process, an analogy is formed between word forms within an inflectional paradigm but also across paradigms. As neural network models for inflection are typically trained only on lemma-target form pairs, we propose three new ways to provide neural models with additional source forms to strengthen analogy-formation, and compare our methods to other approaches in the literature. We show that the proposed methods of providing a Transformer sequence-to-sequence model with additional analogy sources in the input are consistently effective, and improve upon recent state-of-the-art results on 46 languages, particularly in low-resource settings. We also propose a method to combine the analogy-motivated approach with data hallucination or augmentation. We find that the two approaches are complementary to each other and combining the two approaches is especially helpful when the training data is extremely limited.

In this paper, we evaluate the progress of our field toward solving simple factoid questions over a knowledge base, a practically important problem in natural language interface to database. As in other natural language understanding tasks, a common practice for this task is to train and evaluate a model on a single dataset, and recent studies suggest that SimpleQuestions, the most popular and largest dataset, is nearly solved under this setting. However, this common setting does not evaluate the robustness of the systems outside of the distribution of the used training data. We rigorously evaluate such robustness of existing systems using different datasets. Our analysis, including shifting of training and test datasets and training on a union of the datasets, suggests that our progress in solving SimpleQuestions dataset does not indicate the success of more general simple question answering. We discuss a possible future direction toward this goal.

We conduct a linguistic analysis of recent metaphor recognition systems, all of which are based on language models. We show that their performance, although reaching high F-scores, has considerable gaps from a linguistic perspective. First, they perform substantially worse on unconventional metaphors than on conventional ones. Second, they struggle with handling rarer word types. These two findings together suggest that a large part of the systems’ success is due to optimising the disambiguation of conventionalised, metaphoric word senses for specific words instead of modelling general properties of metaphors. As a positive result, the systems show increasing capabilities to recognise metaphoric readings of unseen words if synonyms or morphological variations of these words have been seen before, leading to enhanced generalisation beyond word sense disambiguation.

This paper explores an unsupervised approach to learning a compositional representation function for multi-word expressions (MWEs), and evaluates it on the Tratz dataset, which associates two-word expressions with the semantic relation between the compound constituents (e.g. the label employer is associated with the noun compound government agency) (Tratz, 2011). The composition function is based on recurrent neural networks, and is trained using the Skip-Gram objective to predict the words in the context of MWEs. Thus our approach can naturally leverage large unlabeled text sources. Further, our method can make use of provided MWEs when available, but can also function as a completely unsupervised algorithm, using MWE boundaries predicted by a single, domain-agnostic part-of-speech pattern. With pre-defined MWE boundaries, our method outperforms the previous state-of-the-art performance on the coarse-grained evaluation of the Tratz dataset (Tratz, 2011), with an F1 score of 50.4%. The unsupervised version of our method approaches the performance of the supervised one, and even outperforms it in some configurations.

This demo paper introduces the online Readability Leveled Arabic Thesaurus interface. For a given user input word, this interface provides the word’s possible lemmas, roots, English glosses, related Arabic words and phrases, and readability on a five-level readability scale. This interface builds on and connects multiple existing Arabic resources and processing tools. This one-of-a-kind system enables Arabic speakers and learners to benefit from advances in Arabic computational linguistics technologies. Feedback from users of the system will help the developers to identify lexical coverage gaps and errors. A live link to the demo is available at: http://samer.camel-lab.com/.

Emotion recognition in conversations (ERC) has received much attention recently in the natural language processing community. Considering that the emotions of the utterances in conversations are interactive, previous works usually implicitly model the emotion interaction between utterances by modeling dialogue context, but the misleading emotion information from context often interferes with the emotion interaction. We noticed that the gold emotion labels of the context utterances can provide explicit and accurate emotion interaction, but it is impossible to input gold labels at inference time. To address this problem, we propose an iterative emotion interaction network, which uses iteratively predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. This approach solves the above problem, and can effectively retain the performance advantages of explicit modeling. We conduct experiments on two datasets, and our approach achieves state-of-the-art performance.

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage. In this study, we evaluate those state-of-the-art methods in an industrial context, where the impact of seed mappings with different sizes and different biases is explored. Besides the popular benchmarks from DBpedia and Wikidata, we contribute and evaluate a new industrial benchmark that is extracted from two heterogeneous knowledge graphs (KGs) under deployment for medical applications. The experimental results enable the analysis of the advantages and disadvantages of these alignment methods and the further discussion of suitable strategies for their industrial deployment.

Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external knowledge to assist the understanding of the scenario for better description generation. We integrate two additional modules into the pretrained encoder-decoder model for prototype modeling to enhance the knowledge injection procedure. We conduct experiment on CommonGen benchmark, experimental results show that our method significantly improves the performance on all the metrics.

The topic of this paper is neural multi-task training for text style transfer. We present an efficient method for neutral-to-style transformation using the transformer framework. We demonstrate how to prepare a robust model utilizing large paraphrases corpora together with a small parallel style transfer corpus. We study how much style transfer data is needed for a model on the example of two transformations: neutral-to-cute on internal corpus and modern-to-antique on publicly available Bible corpora. Additionally, we propose a synthetic measure for the automatic evaluation of style transfer models. We hope our research is a step towards replacing common but limited rule-based style transfer systems by more flexible machine learning models for both public and commercial usage.

While pre-trained word embeddings have been shown to improve the performance of downstream tasks, many questions remain regarding their reliability: Do the same pre-trained word embeddings result in the best performance with slight changes to the training data? Do the same pre-trained embeddings perform well with multiple neural network architectures? Do imputation strategies for unknown words impact reliability? In this paper, we introduce two new metrics to understand the downstream reliability of word embeddings. We find that downstream reliability of word embeddings depends on multiple factors, including, the evaluation metric, the handling of out-of-vocabulary words, and whether the embeddings are fine-tuned.

One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a state-of-the-art data augmentation method, called the contextual data augmentation (CDA), that generates labeled training instances using a pretrained language model. The CDA has been reported to work well for several other natural language processing tasks, including text classification and machine translation. This study addresses two underexplored issues on CDA, that is, how to reduce the computational cost of data augmentation and how to ensure the quality of the generated data. We also propose two methods to adapt CDA to ZAR: [MASK]-based augmentation and linguistically-controlled masking. Consequently, the experimental results on Japanese ZAR show that our methods contribute to both the accuracy gainand the computation cost reduction. Our closer analysis reveals that the proposed method can improve the quality of the augmented training data when compared to the conventional CDA.

The widespread adoption of reference-based automatic evaluation metrics such as ROUGE has promoted the development of document summarization. In this paper, we consider a new protocol for designing reference-based metrics that require the endorsement of source document(s). Following protocol, we propose an anchored ROUGE metric fixing each summary particle on source document, which bases the computation on more solid ground. Empirical results on benchmark datasets validate that source document helps to induce a higher correlation with human judgments for ROUGE metric. Being self-explanatory and easy-to-implement, the protocol can naturally foster various effective designs of reference-based metrics besides the anchored ROUGE introduced here.

Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity recognition, which is usually modeled as a token-level sequence labeling problem. Through experiments on two data sets from the biomedical and materials science domains (i2b2-2010 and MaSciP), we show that simple augmentation can boost performance for both recurrent and transformer-based models, especially for small training sets.

The Winograd Schema Challenge (WSC) and variants inspired by it have become important benchmarks for common-sense reasoning (CSR). Model performance on the WSC has quickly progressed from chance-level to near-human using neural language models trained on massive corpora. In this paper, we analyze the effects of varying degrees of overlaps that occur between these corpora and the test instances in WSC-style tasks. We find that a large number of test instances overlap considerably with the pretraining corpora on which state-of-the-art models are trained, and that a significant drop in classification accuracy occurs when models are evaluated on instances with minimal overlap. Based on these results, we provide the WSC-Web dataset, consisting of over 60k pronoun disambiguation problems scraped from web data, being both the largest corpus to date, and having a significantly lower proportion of overlaps with current pretraining corpora.

Lexical substitution, i.e. generation of plausible words that can replace a particular target word in a given context, is an extremely powerful technology that can be used as a backbone of various NLP applications, including word sense induction and disambiguation, lexical relation extraction, data augmentation, etc. In this paper, we present a large-scale comparative study of lexical substitution methods employing both rather old and most recent language and masked language models (LMs and MLMs), such as context2vec, ELMo, BERT, RoBERTa, XLNet. We show that already competitive results achieved by SOTA LMs/MLMs can be further substantially improved if information about the target word is injected properly. Several existing and new target word injection methods are compared for each LM/MLM using both intrinsic evaluation on lexical substitution datasets and extrinsic evaluation on word sense induction (WSI) datasets. On two WSI datasets we obtain new SOTA results. Besides, we analyze the types of semantic relations between target words and their substitutes generated by different models or given by annotators.