EMNLP 2020 Papers

Code-mixing, the interleaving of two or more languages within a sentence or discourse is ubiquitous in multilingual societies. The lack of code-mixed training data is one of the major concerns for the development of end-to-end neural network-based models to be deployed for a variety of natural language processing (NLP) applications. A potential solution is to either manually create or crowd-source the code-mixed labelled data for the task at hand, but that requires much human efforts and often not feasible because of the language specific diversity in the code-mixed text. To circumvent the data scarcity issue, we propose an effective deep learning approach for automatically generating the code-mixed text from English to multiple languages without any parallel data. In order to train the neural network, we create synthetic code-mixed texts from the available parallel corpus by modelling various linguistic properties of code-mixing. Our codemixed text generator is built upon the encoder-decoder framework, where the encoder is augmented with the linguistic and task-agnostic features obtained from the transformer based language model. We also transfer the knowledge from a neural machine translation (NMT) to warm-start the training of code-mixed generator. Experimental results and in-depth analysis show the effectiveness of our proposed code-mixed text generation on eight diverse language pairs.

Using a single encoder and decoder for all directions and training with English-centric data is a popular scheme for multilingual NMT. However, zero-shot translation under this scheme is vulnerable to changes in training conditions, as the model degenerates by decoding non-English texts into English regardless of the target specifier token. We present that enforcing both sparsity and decorrelation on encoder intermediate representations with the SLNI regularizer (Aljundi et al., 2019) efficiently mitigates this problem, without performance loss in supervised directions. Notably, effects of SLNI turns out to be irrelevant to promoting language-invariance in encoder representations.

This paper problematizes the reliance on documents as the basic notion for defining term interactions in standard topic models. As an alternative to this practice, we reformulate topic distributions as latent factors in term similarity space. We exemplify the idea using a number of standard word embeddings built with very wide context windows. The embedding spaces are transformed to sparse similarity spaces, and topics are extracted in standard fashion by factorizing to a lower-dimensional space. We use a number of different factorization techniques, and evaluate the various models using a large set of evaluation metrics, including previously published coherence measures, as well as a number of novel measures that we suggest better correspond to real-world applications of topic models. Our results clearly demonstrate that term-based models outperform standard document-based models by a large margin.

It is well-known that abstractive summaries are subject to hallucination—including material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases, such summaries would fail to be very informative. Alternatively, one can try to avoid hallucinations by verifying that any specific entities in the summary appear in the original text in a similar context. This is the approach taken by our system, Herman. The system learns to recognize and verify quantity entities (dates, numbers, sums of money, etc.) in a beam-worth of abstractive summaries produced by state-of-the-art models, in order to up-rank those summaries whose quantity terms are supported by the original text. Experimental results demonstrate that the ROUGE scores of such up-ranked summaries have a higher Precision than summaries that have not been up-ranked, without a comparable loss in Recall, resulting in higher F1. Preliminary human evaluation of up-ranked vs. original summaries shows people’s preference for the former.

Automated generation of medical reports that describe the findings in the medical images helps radiologists by alleviating their workload. Medical report generation system should generate correct and concise reports. However, data imbalance makes it difficult to train models accurately. Medical datasets are commonly imbalanced in their finding labels because incidence rates differ among diseases; moreover, the ratios of abnormalities to normalities are significantly imbalanced. We propose a novel reinforcement learning method with a reconstructor to improve the clinical correctness of generated reports to train the data-to-text module with a highly imbalanced dataset. Moreover, we introduce a novel data augmentation strategy for reinforcement learning to additionally train the model on infrequent findings. From the perspective of a practical use, we employ a Two-Stage Medical Report Generator (TS-MRGen) for controllable report generation from input images. TS-MRGen consists of two separated stages: an image diagnosis module and a data-to-text module. Radiologists can modify the image diagnosis module results to control the reports that the data-to-text module generates. We conduct an experiment with two medical datasets to assess the data-to-text module and the entire two-stage model. Results demonstrate that the reports generated by our model describe the findings in the input image more correctly.

The information retrieval from relational database requires professionals who has an understanding of structural query language such as SQL. TEXT2SQL models apply natural language inference to enable user interacting the database via natural language utterance. Current TEXT2SQL models normally focus on generating complex SQL query in a precise and complete fashion while certain features of real-world application in the production environment is not fully addressed. This paper is aimed to develop a service-oriented Text-to-SQL parser that translates natural language utterance to structural and executable SQL query. We introduce a algorithmic framework named Semantic-Enriched SQL generator (SE-SQL) that enables flexibly access database than rigid API in the application while keeping the performance quality for the most commonly used cases. The qualitative result shows that the proposed model achieves 88.3% execution accuracy on WikiSQL task, outperforming baseline by 13% error reduction. Moreover, the framework considers several service-oriented needs including low-complexity inference, out-of-table rejection, and text normalization.

Early intervention for suicide risks with social media data has increasingly received great attention. Using a suicide dictionary created by mental health experts is one of the effective ways to detect suicidal ideation. However, little attention has been paid to validate whether and how the existing dictionaries for other languages (i.e., English and Chinese) can be used for predicting suicidal ideation for a low-resource language (i.e., Korean) where a knowledge-based suicide dictionary has not yet been developed. To this end, we propose a cross-lingual suicidal ideation detection model that can identify whether a given social media post includes suicidal ideation or not. To utilize the existing suicide dictionaries developed for other languages (i.e., English and Chinese) in word embedding, our model translates a post written in the target language (i.e., Korean) into English and Chinese, and then uses the separate suicidal-oriented word embeddings developed for English and Chinese, respectively. By applying an ensemble approach for different languages, the model achieves high accuracy, over 87%. We believe our model is useful in accessing suicidal ideation using social media data for preventing potential suicide risk in an early stage.

Abstract Meaning Representation (AMR) parsing aims at converting sentences into AMR representations. These are graphs and not trees because AMR supports reentrancies (nodes with more than one parent). Following previous findings on the importance of reen- trancies for AMR, we empirically find and discuss several linguistic phenomena respon- sible for reentrancies in AMR, some of which have not received attention before. We cate- gorize the types of errors AMR parsers make with respect to reentrancies. Furthermore, we find that correcting these errors provides an in- crease of up to 5% Smatch in parsing perfor- mance and 20% in reentrancy prediction

Extracting rationales can help human understand which information the model utilizes and how it makes the prediction towards better interpretability. However, annotating rationales requires much effort and only few datasets contain such labeled rationales, making supervised learning for rationalization difficult. In this paper, we propose a novel approach that leverages the benefits of both multi-task learning and transfer learning for generating rationales through question answering in a zero-shot fashion. For two benchmark rationalization datasets, the proposed method achieves comparable or even better performance of rationalization without any supervised signal, demonstrating the great potential of zero-shot rationalization for better interpretability.

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators needs to be manually closed by post-editing. In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. Our goal is to provide error correction suggestions and to further relieve the burden of human translators through an interpretable model. To imitate the behavior of human translators, we design three efficient delegation modules – quality estimation, generative post-editing, and atomic operation post-editing and construct a hierarchical model based on them. We examine this approach with the English–German dataset from WMT 2017 APE shared task and our experimental results can achieve the state-of-the-art performance. We also verify that the certified translators can significantly expedite their post-editing processing with our model in human evaluation.

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from Transformers), a pretraining framework for conversational tasks satisfying all the following requirements: it is effective, affordable, and quick to train. We pretrain using a retrieval-based response selection task, effectively leveraging quantization and subword-level parameterization in the dual encoder to build a lightweight memory- and energy-efficient model. We show that ConveRT achieves state-of-the-art performance across widely established response selection tasks. We also demonstrate that the use of extended dialog history as context yields further performance gains. Finally, we show that pretrained representations from the proposed encoder can be transferred to the intent classification task, yielding strong results across three diverse data sets. ConveRT trains substantially faster than standard sentence encoders or previous state-of-the-art dual encoders. With its reduced size and superior performance, we believe this model promises wider portability and scalability for Conversational AI applications.

Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. ‘Low-resourced’-ness is a complex problem going beyond data availability and reflects systemic problems in society. In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and communication worldwide. Despite immense improvements in MT over the past decade, MT is centered around a few high-resourced languages. As MT researchers cannot solve the problem of low-resourcedness alone, we propose participatory research as a means to involve all necessary agents required in the MT development process. We demonstrate the feasibility and scalability of participatory research with a case study on MT for African languages. Its implementation leads to a collection of novel translation datasets, MT benchmarks for over 30 languages, with human evaluations for a third of them, and enables participants without formal training to make a unique scientific contribution. Benchmarks, models, data, code, and evaluation results are released at https://github.com/masakhane-io/masakhane-mt.

Generating questions based on answers and relevant contexts is a challenging task. Recent work mainly pays attention to the quality of a single generated question. However, question generation is actually a one-to-many problem, as it is possible to raise questions with different focuses on contexts and various means of expression. In this paper, we explore the diversity of question generation and come up with methods from these two aspects. Specifically, we relate contextual focuses with content selectors, which are modeled by a continuous latent variable with the technique of conditional variational auto-encoder (CVAE). In the realization of CVAE, a multimodal prior distribution is adopted to allow for more diverse content selectors. To take into account various means of expression, question types are explicitly modeled and a diversity-promoting algorithm is proposed further. Experimental results on public datasets show that our proposed method can significantly improve the diversity of generated questions, especially from the perspective of using different question types. Overall, our proposed method achieves a better trade-off between generation quality and diversity compared with existing approaches.

We consider the task of cross-lingual adaptation of dependency parsers without annotated target corpora and parallel corpora. Previous work either directly applies a discriminative source parser to the target language, ignoring unannotated target corpora, or employs an unsupervised generative parser that can leverage unannotated target data but has weaker representational power than discriminative parsers. In this paper, we propose to utilize unsupervised discriminative parsers based on the CRF autoencoder framework for this task. We train a source parser and use it to initialize and regularize a target parser that is trained on unannotated target data. We conduct experiments that transfer an English parser to 20 target languages. The results show that our method significantly outperforms previous methods.

Neural response generative models have achieved remarkable progress in recent years but tend to yield irrelevant and uninformative responses. One of the reasons is that encoder-decoder based models always use a single decoder to generate a complete response at a stroke. This tends to generate high-frequency function words with less semantic information rather than low-frequency content words with more semantic information. To address this issue, we propose a content-aware model with two-stage decoding process named Two-stage Dialogue Generation (TSDG). We separate the decoding process of content words and function words so that content words can be generated independently without the interference of function words. Experimental results on two datasets indicate that our model significantly outperforms several competitive generative models in terms of automatic and human evaluation.

Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their content. Previous work studying figures in scientific papers focused on classifying figure content rather than understanding how images relate to the text. To address challenges in figure retrieval and figure-to-text alignment, we introduce MedICaT, a dataset of medical images in context. MedICaT consists of 217K images from 131K open access biomedical papers, and includes captions, inline references for 74% of figures, and manually annotated subfigures and subcaptions for a subset of figures. Using MedICaT, we introduce the task of subfigure to subcaption alignment in compound figures and demonstrate the utility of inline references in image-text matching. Our data and code can be accessed at https://github.com/allenai/medicat.

Previous studies on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an NLG system to describe interesting facts from logical inferences across records. If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations. In this work, we formulate high-fidelity NLG as generation from logical forms in order to obtain controllable and faithful generations. We present a new large-scale dataset, Logic2Text, with 10,753 descriptions involving common logic types paired with the underlying logical forms. The logical forms show diversified graph structure of free schema, which pose great challenges on the model’s ability to understand the semantics. We experiment on (1) Fully-supervised training with the full datasets, and (2) Few-shot setting, provided with hundreds of paired examples; We compare several popular generation models and analyze their performances. We hope our dataset can encourage research towards building an advanced NLG system capable of natural, faithful, and human-like generation. The dataset and code is available at https://github.com/czyssrs/Logic2Text.

The extraction of interactions between chemicals and proteins from several biomedical articles is important in many fields of biomedical research such as drug development and prediction of drug side effects. Several natural language processing methods, including deep neural network (DNN) models, have been applied to address this problem. However, these methods were trained with hard-labeled data, which tend to become over-confident, leading to degradation of the model reliability. To estimate the data uncertainty and improve the reliability, “calibration” techniques have been applied to deep learning models. In this study, to extract chemical–protein interactions, we propose a DNN-based approach incorporating uncertainty information and calibration techniques. Our model first encodes the input sequence using a pre-trained language-understanding model, following which it is trained using two calibration methods: mixup training and addition of a confidence penalty loss. Finally, the model is re-trained with augmented data that are extracted using the estimated uncertainties. Our approach has achieved state-of-the-art performance with regard to the Biocreative VI ChemProt task, while preserving higher calibration abilities than those of previous approaches. Furthermore, our approach also presents the possibilities of using uncertainty estimation for performance improvement.

The goal of text summarization is to compress documents to the relevant information while excluding background information already known to the receiver. So far, summarization researchers have given considerably more attention to relevance than to background knowledge. In contrast, this work puts background knowledge in the foreground. Building on the realization that the choices made by human summarizers and annotators contain implicit information about their background knowledge, we develop and compare techniques for inferring background knowledge from summarization data. Based on this framework, we define summary scoring functions that explicitly model background knowledge, and show that these scoring functions fit human judgments significantly better than baselines. We illustrate some of the many potential applications of our framework. First, we provide insights into human information importance priors. Second, we demonstrate that averaging the background knowledge of multiple, potentially biased annotators or corpora greatly improves summaryscoring performance. Finally, we discuss potential applications of our framework beyond summarization.