EMNLP 2018 Papers

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem would benefit many downstream tasks such as to translate text classification models from resource-rich languages (e.g. English) to low-resource languages. Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages. This paper proposes an unsupervised learning approach that does not require any cross-lingual labeled data. Given two monolingual word embedding spaces for any language pair, our algorithm optimizes the transformation functions in both directions simultaneously based on distributional matching as well as minimizing the back-translation losses. We use a neural network implementation to calculate the Sinkhorn distance, a well-defined distributional similarity measure, and optimize our objective through back-propagation. Our evaluation on benchmark datasets for bilingual lexicon induction and cross-lingual word similarity prediction shows stronger or competitive performance of the proposed method compared to other state-of-the-art supervised and unsupervised baseline methods over many language pairs.

In this paper we advocate the use of bilingual corpora which are abundantly available for training sentence compression models. Our approach borrows much of its machinery from neural machine translation and leverages bilingual pivoting: compressions are obtained by translating a source string into a foreign language and then back-translating it into the source while controlling the translation length. Our model can be trained for any language as long as a bilingual corpus is available and performs arbitrary rewrites without access to compression specific data. We release. Moss, a new parallel Multilingual Compression dataset for English, German, and French which can be used to evaluate compression models across languages and genres.

Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm. We propose effective and general solutions to each of them. Using policy shaping, we bias the search procedure towards semantic parses that are more compatible to the text, which provide better supervision signals for training. In addition, we propose an update equation that generalizes three different families of learning algorithms, which enables fast model exploration. When experimented on a recently proposed sequential question answering dataset, our framework leads to a new state-of-the-art model that outperforms previous work by 5.0% absolute on exact match accuracy.

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is interpreted as the latent dependency between the natural language words in our joint representation. Such dependency information can capture the interactions between the semantics and natural language words. We integrate a neural component into our model and propose an efficient dynamic-programming algorithm to perform tractable inference. Through extensive experiments on the standard multilingual GeoQuery dataset with eight languages, we demonstrate that our proposed approach is able to achieve state-of-the-art performance across several languages. Analysis also justifies the effectiveness of using our new dependency-based representation.

In this paper, we propose a new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser. Our aligner is further tuned by our oracle parser via picking the alignment that leads to the highest-scored achievable AMR graph. Experimental results show that our aligner outperforms the rule-based aligner in previous work by achieving higher alignment F1 score and consistently improving two open-sourced AMR parsers. Based on our aligner and transition system, we develop a transition-based AMR parser that parses a sentence into its AMR graph directly. An ensemble of our parsers with only words and POS tags as input leads to 68.4 Smatch F1 score, which outperforms the current state-of-the-art parser.

We propose a novel approach to semantic dependency parsing (SDP) by casting the task as an instance of multi-lingual machine translation, where each semantic representation is a different foreign dialect. To that end, we first generalize syntactic linearization techniques to account for the richer semantic dependency graph structure. Following, we design a neural sequence-to-sequence framework which can effectively recover our graph linearizations, performing almost on-par with previous SDP state-of-the-art while requiring less parallel training annotations. Beyond SDP, our linearization technique opens the door to integration of graph-based semantic representations as features in neural models for downstream applications.

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.

We propose a new dataset for evaluating question answering models with respect to their capacity to reason about beliefs. Our tasks are inspired by theory-of-mind experiments that examine whether children are able to reason about the beliefs of others, in particular when those beliefs differ from reality. We evaluate a number of recent neural models with memory augmentation. We find that all fail on our tasks, which require keeping track of inconsistent states of the world; moreover, the models’ accuracy decreases notably when random sentences are introduced to the tasks at test.

We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of 1326 elementary level science facts. Roughly 6000 questions probe an understanding of these facts and their application to novel situations. This requires combining an open book fact (e.g., metals conduct electricity) with broad common knowledge (e.g., a suit of armor is made of metal) obtained from other sources. While existing QA datasets over documents or knowledge bases, being generally self-contained, focus on linguistic understanding, OpenBookQA probes a deeper understanding of both the topic—in the context of common knowledge—and the language it is expressed in. Human performance on OpenBookQA is close to 92%, but many state-of-the-art pre-trained QA methods perform surprisingly poorly, worse than several simple neural baselines we develop. Our oracle experiments designed to circumvent the knowledge retrieval bottleneck demonstrate the value of both the open book and additional facts. We leave it as a challenge to solve the retrieval problem in this multi-hop setting and to close the large gap to human performance.

Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowing QA systems to reason with strong supervision and explain the predictions; (4) we offer a new type of factoid comparison questions to test QA systems’ ability to extract relevant facts and perform necessary comparison. We show that HotpotQA is challenging for the latest QA systems, and the supporting facts enable models to improve performance and make explainable predictions.

We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million questions-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline models for question to logical form and question to answer mapping.

Cloze tests are widely adopted in language exams to evaluate students’ language proficiency. In this paper, we propose the first large-scale human-created cloze test dataset CLOTH, containing questions used in middle-school and high-school language exams. With missing blanks carefully created by teachers and candidate choices purposely designed to be nuanced, CLOTH requires a deeper language understanding and a wider attention span than previously automatically-generated cloze datasets. We test the performance of dedicatedly designed baseline models including a language model trained on the One Billion Word Corpus and show humans outperform them by a significant margin. We investigate the source of the performance gap, trace model deficiencies to some distinct properties of CLOTH, and identify the limited ability of comprehending the long-term context to be the key bottleneck.

We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing $50) and the execution of that strategy (e.g., generating “The bike is brand new. Selling for just $50!”). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse dialogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence generation task (i.e., given a sequence of utterances generate the response sequence). This is not only an overly simplistic view of conversation but it is also emphatically different from the way humans converse by heavily relying on their background knowledge about the topic (as opposed to simply relying on the previous sequence of utterances). For example, it is common for humans to (involuntarily) produce utterances which are copied or suitably modified from background articles they have read about the topic. To facilitate the development of such natural conversation models which mimic the human process of conversing, we create a new dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie. We establish baseline results on this dataset (90K utterances from 9K conversations) using three different models: (i) pure generation based models which ignore the background knowledge (ii) generation based models which learn to copy information from the background knowledge when required and (iii) span prediction based models which predict the appropriate response span in the background knowledge.

Modern automated dialog systems require complex dialog managers able to deal with user intent triggered by high-level semantic questions. In this paper, we propose a model for automatically clustering questions into user intents to help the design tasks. Since questions are short texts, uncovering their semantics to group them together can be very challenging. We approach the problem by using powerful semantic classifiers from question duplicate/matching research along with a novel idea of supervised clustering methods based on structured output. We test our approach on two intent clustering corpora, showing an impressive improvement over previous methods for two languages/domains.

Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We demonstrate our method by building a dialogue agent for the composite task of travel planning. Experiments with simulated and real users show that our approach performs competitively against a state-of-the-art method that requires human-defined subgoals. Moreover, we show that the learned subgoals are often human comprehensible.

Referring to entities in situated dialog is a collaborative process, whereby interlocutors often expand, repair and/or replace referring expressions in an iterative process, converging on conceptual pacts of referring language use in doing so. Nevertheless, much work on exophoric reference resolution (i.e. resolution of references to entities outside of a given text) follows a literary model, whereby individual referring expressions are interpreted as unique identifiers of their referents given the state of the dialog the referring expression is initiated. In this paper, we address this collaborative nature to improve dialogic reference resolution in two ways: First, we trained a words-as-classifiers logistic regression model of word semantics and incrementally adapt the model to idiosyncratic language between dyad partners during evaluation of the dialog. We then used these semantic models to learn the general referring ability of each word, which is independent of referent features. These methods facilitate accurate automatic reference resolution in situated dialog without annotation of referring expressions, even with little background data.

This paper presents a corpus and experimental results to extract possession relations over time. We work with Wikipedia articles about artworks, and extract possession relations along with temporal information indicating when these relations are true. The annotation scheme yields many possessors over time for a given artwork, and experimental results show that an LSTM ensemble can automate the task.

Experimental performance on the task of relation classification has generally improved using deep neural network architectures. One major drawback of reported studies is that individual models have been evaluated on a very narrow range of datasets, raising questions about the adaptability of the architectures, while making comparisons between approaches difficult. In this work, we present a systematic large-scale analysis of neural relation classification architectures on six benchmark datasets with widely varying characteristics. We propose a novel multi-channel LSTM model combined with a CNN that takes advantage of all currently popular linguistic and architectural features. Our ‘Man for All Seasons’ approach achieves state-of-the-art performance on two datasets. More importantly, in our view, the model allowed us to obtain direct insights into the continued challenges faced by neural language models on this task.