EMNLP 2019 Papers

Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dimensions for probabilistic word embeddings. Experimental results show that sensible priors can capture latent semantic concepts better than or on-par with the current state of the art, while retaining the simplicity and generalizability of using priors.

Twitter is used for various applications such as disaster monitoring and news material gathering. In these applications, each Tweet is classified into pre-defined classes. These classes have a semantic relationship with each other and can be classified into a hierarchical structure, which is regarded as important information. Label texts of pre-defined classes themselves also include important clues for classification. Therefore, we propose a method that can consider the hierarchical structure of labels and label texts themselves. We conducted evaluation over the Text REtrieval Conference (TREC) 2018 Incident Streams (IS) track dataset, and we found that our method outperformed the methods of the conference participants.

Flipping sentiment while preserving sentence meaning is challenging because parallel sentences with the same content but different sentiment polarities are not always available for model learning. We introduce a method for acquiring imperfectly aligned sentences from non-parallel corpora and propose a model that learns to minimize the sentiment and content losses in a fully end-to-end manner. Our model is simple and offers well-balanced results across two domains: Yelp restaurant and Amazon product reviews.

Based on massive amounts of data, recent pretrained contextual representation models have made significant strides in advancing a number of different English NLP tasks. However, for other languages, relevant training data may be lacking, while state-of-the-art deep learning methods are known to be data-hungry. In this paper, we present an elegantly simple robust self-learning framework to include unlabeled non-English samples in the fine-tuning process of pretrained multilingual representation models. We leverage a multilingual model’s own predictions on unlabeled non-English data in order to obtain additional information that can be used during further fine-tuning. Compared with original multilingual models and other cross-lingual classification models, we observe significant gains in effectiveness on document and sentiment classification for a range of diverse languages.

Stance detection aims to detect whether the opinion holder is in support of or against a given target. Recent works show improvements in stance detection by using either the attention mechanism or sentiment information. In this paper, we propose a multi-task framework that incorporates target-specific attention mechanism and at the same time takes sentiment classification as an auxiliary task. Moreover, we used a sentiment lexicon and constructed a stance lexicon to provide guidance for the attention layer. Experimental results show that the proposed model significantly outperforms state-of-the-art deep learning methods on the SemEval-2016 dataset.

We introduce a new dataset for multi-class emotion analysis from long-form narratives in English. The Dataset for Emotions of Narrative Sequences (DENS) was collected from both classic literature available on Project Gutenberg and modern online narratives avail- able on Wattpad, annotated using Amazon Mechanical Turk. A number of statistics and baseline benchmarks are provided for the dataset. Of the tested techniques, we find that the fine-tuning of a pre-trained BERT model achieves the best results, with an average micro-F1 score of 60.4%. Our results show that the dataset provides a novel opportunity in emotion analysis that requires moving beyond existing sentence-level techniques.

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of learning with noisy labels for sentence-level sentiment classification. We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training. NetAb consists of two convolutional neural networks, one with a noise transition layer for dealing with the input noisy labels and the other for predicting ‘clean’ labels. We train the two networks using their respective loss functions in a mutual reinforcement manner. Experimental results demonstrate the effectiveness of the proposed model.

Aspect-based sentiment analysis (ABSA) has attracted increasing attention recently due to its broad applications. In existing ABSA datasets, most sentences contain only one aspect or multiple aspects with the same sentiment polarity, which makes ABSA task degenerate to sentence-level sentiment analysis. In this paper, we present a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities. The release of this dataset would push forward the research in this field. In addition, we propose simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances. Experiments on our new dataset show that the proposed model significantly outperforms the state-of-the-art baseline methods

In online arguments, identifying how users construct their arguments to persuade others is important in order to understand a persuasive strategy directly. However, existing research lacks empirical investigations on highly semantic aspects of elementary units (EUs), such as propositions for a persuasive online argument. Therefore, this paper focuses on a pilot study, revealing a persuasion strategy using EUs. Our contributions are as follows: (1) annotating five types of EUs in a persuasive forum, the so-called ChangeMyView, (2) revealing both intuitive and non-intuitive strategic insights for the persuasion by analyzing 4612 annotated EUs, and (3) proposing baseline neural models that identify the EU boundary and type. Our observations imply that EUs definitively characterize online persuasion strategies.

The task of entity recognition has traditionally been modelled as a sequence labelling task. However, this usually requires a large amount of fine-grained data annotated at the token level, which in turn can be expensive and cumbersome to obtain. In this work, we aim to circumvent this requirement of word-level annotated data. To achieve this, we propose a novel architecture for entity recognition from a corpus containing weak binary presence/absence labels, which are relatively easier to obtain. We show that our proposed weakly supervised model, trained solely on a multi-label classification task, performs reasonably well on the task of entity recognition, despite not having access to any token-level ground truth data.

Open Information Extraction (Open IE) systems have been traditionally evaluated via manual annotation. Recently, an automated evaluator with a benchmark dataset (OIE2016) was released – it scores Open IE systems automatically by matching system predictions with predictions in the benchmark dataset. Unfortunately, our analysis reveals that its data is rather noisy, and the tuple matching in the evaluator has issues, making the results of automated comparisons less trustworthy. We contribute CaRB, an improved dataset and framework for testing Open IE systems. To the best of our knowledge, CaRB is the first crowdsourced Open IE dataset and it also makes substantive changes in the matching code and metrics. NLP experts annotate CaRB’s dataset to be more accurate than OIE2016. Moreover, we find that on one pair of Open IE systems, CaRB framework provides contradictory results to OIE2016. Human assessment verifies that CaRB’s ranking of the two systems is the accurate ranking. We release the CaRB framework along with its crowdsourced dataset.

For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, it is such a strong signal that model performance on these tasks drops sharply in common lowercased scenarios, such as noisy web text or machine translation outputs. In this work, we perform a systematic analysis of solutions to this problem, modifying only the casing of the train or test data using lowercasing and truecasing methods. While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text. As shown in our experiments, this result holds across tasks and input representations. Finally, we show that our proposed solution gives an 8% F1 improvement in mention detection on noisy out-of-domain Twitter data.

We present FewRel 2.0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances? (2) Can they detect none-of-the-above (NOTA) relations? To construct FewRel 2.0, we build upon the FewRel dataset by adding a new test set in a quite different domain, and a NOTA relation choice. With the new dataset and extensive experimental analysis, we found (1) that the state-of-the-art few-shot relation classification models struggle on these two aspects, and (2) that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well. Our research calls for more attention and further efforts to these two real-world issues. All details and resources about the dataset and baselines are released at https://github.com/thunlp/fewrel.

We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical com- pound paraphrase model. Our method en- ables the long short-term memory (LSTM) of the NER model to capture chemical com- pound paraphrases by sharing the parameters of the LSTM and character embeddings be- tween the two models. The experimental re- sults on the BioCreative IV’s CHEMDNER task show that our method improves chemi- cal NER and achieves state-of-the-art perfor- mance.

Attributing a particular property to a person by naming another person, who is typically wellknown for the respective property, is called a Vossian Antonomasia (VA). This subtpye of metonymy, which overlaps with metaphor, has a specific syntax and is especially frequent in journalistic texts. While identifying Vossian Antonomasia is of particular interest in the study of stylistics, it is also a source of errors in relation and fact extraction as an explicitly mentioned entity occurs only metaphorically and should not be associated with respective contexts. Despite rather simple syntactic variations, the automatic extraction of VA was never addressed as yet since it requires a deeper semantic understanding of mentioned entities and underlying relations. In this paper, we propose a first method for the extraction of VAs that works completely automatically. Our approaches use named entity recognition, distant supervision based on Wikidata, and a bi-directional LSTM for postprocessing. The evaluation on 1.8 million articles of the New York Times corpus shows that our approach significantly outperforms the only existing semi-automatic approach for VA identification by more than 30 percentage points in precision.

Current region-based NER models only rely on fully-annotated training data to learn effective region encoder, which often face the training data bottleneck. To alleviate this problem, this paper proposes Gazetteer-Enhanced Attentive Neural Networks, which can enhance region-based NER by learning name knowledge of entity mentions from easily-obtainable gazetteers, rather than only from fully-annotated data. Specially, we first propose an attentive neural network (ANN), which explicitly models the mention-context association and therefore is convenient for integrating externally-learned knowledge. Then we design an auxiliary gazetteer network, which can effectively encode name regularity of mentions only using gazetteers. Finally, the learned gazetteer network is incorporated into ANN for better NER. Experiments show that our ANN can achieve the state-of-the-art performance on ACE2005 named entity recognition benchmark. Besides, incorporating gazetteer network can further improve the performance and significantly reduce the requirement of training data.

Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored. Current state-of-the-art n-ary relation extraction method is based on a supervised learning approach and, therefore, may suffer from the lack of sufficient relation labels. In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. To alleviate the sparsity problem and to leverage inherent decomposability of n-ary relations, we propose to learn relation representations of lower-arity facts that result from decomposing higher-arity facts. The proposed method computes a score of a new n-ary fact by aggregating scores of its decomposed lower-arity facts. We conduct experiments with datasets for ternary relation extraction and empirically show that our method improves the n-ary relation extraction performance compared to previous methods.

In medical documents, it is possible that an entity of interest not only contains a discontiguous sequence of words but also overlaps with another entity. Entities of such structures are intrinsically hard to recognize due to the large space of possible entity combinations. In this work, we propose a neural two-stage approach to recognizing discontiguous and overlapping entities by decomposing this problem into two subtasks: 1) it first detects all the overlapping spans that either form entities on their own or present as segments of discontiguous entities, based on the representation of segmental hypergraph, 2) next it learns to combine these segments into discontiguous entities with a classifier, which filters out other incorrect combinations of segments. Two neural components are designed for these subtasks respectively and they are learned jointly using a shared encoder for text. Our model achieves the state-of-the-art performance in a standard dataset, even in the absence of external features that previous methods used.

Fine-grained entity typing is a challenging problem since it usually involves a relatively large tag set and may require to understand the context of the entity mention. In this paper, we use entity linking to help with the fine-grained entity type classification process. We propose a deep neural model that makes predictions based on both the context and the information obtained from entity linking results. Experimental results on two commonly used datasets demonstrates the effectiveness of our approach. On both datasets, it achieves more than 5% absolute strict accuracy improvement over the state of the art.