ACL 2019 论文列表

Automatic article commenting is helpful in encouraging user engagement on online news platforms. However, the news documents are usually too long for models under traditional encoder-decoder frameworks, which often results in general and irrelevant comments. In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph. By organizing the article into graph structure, our model can better understand the internal structure of the article and the connection between topics, which makes it better able to generate coherent and informative comments. We collect and release a large scale news-comment corpus from a popular Chinese online news platform Tencent Kuaibao. Extensive experiment results show that our model can generate much more coherent and informative comments compared with several strong baseline models.

The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 consistently and robustly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5% and 74.7% on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.8% and 9.6%, respectively. Furthermore, our fine-tuned models are also consistently more accurate on the “complex” subsets of WSC273, introduced by Trichelair et al. (2018).

The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commonsense reasoning. We show that the attentions produced by BERT can be directly utilized for tasks such as the Pronoun Disambiguation Problem and Winograd Schema Challenge. Our proposed attention-guided commonsense reasoning method is conceptually simple yet empirically powerful. Experimental analysis on multiple datasets demonstrates that our proposed system performs remarkably well on all cases while outperforming the previously reported state of the art by a margin. While results suggest that BERT seems to implicitly learn to establish complex relationships between entities, solving commonsense reasoning tasks might require more than unsupervised models learned from huge text corpora.

Lexical entailment (LE; also known as hyponymy-hypernymy or is-a relation) is a core asymmetric lexical relation that supports tasks like taxonomy induction and text generation. In this work, we propose a simple and effective method for fine-tuning distributional word vectors for LE. Our Generalized Lexical ENtailment model (GLEN) is decoupled from the word embedding model and applicable to any distributional vector space. Yet – unlike existing retrofitting models – it captures a general specialization function allowing for LE-tuning of the entire distributional space and not only the vectors of words seen in lexical constraints. Coupled with a multilingual embedding space, GLEN seamlessly enables cross-lingual LE detection. We demonstrate the effectiveness of GLEN in graded LE and report large improvements (over 20% in accuracy) over state-of-the-art in cross-lingual LE detection.

Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks. Many of these tasks are of a categorical prediction variety: given a conditioning context (e.g., an NLI premise), provide a label based on an associated prompt (e.g., an NLI hypothesis). The categorical nature of these tasks has led to common use of a cross entropy log-loss objective during training. We suggest this loss is intuitively wrong when applied to plausibility tasks, where the prompt by design is neither categorically entailed nor contradictory given the context. Log-loss naturally drives models to assign scores near 0.0 or 1.0, in contrast to our proposed use of a margin-based loss. Following a discussion of our intuition, we describe a confirmation study based on an extreme, synthetically curated task derived from MultiNLI. We find that a margin-based loss leads to a more plausible model of plausibility. Finally, we illustrate improvements on the Choice Of Plausible Alternative (COPA) task through this change in loss.

We introduce the use of Poincaré embeddings to improve existing state-of-the-art approaches to domain-specific taxonomy induction from text as a signal for both relocating wrong hyponym terms within a (pre-induced) taxonomy as well as for attaching disconnected terms in a taxonomy. This method substantially improves previous state-of-the-art results on the SemEval-2016 Task 13 on taxonomy extraction. We demonstrate the superiority of Poincaré embeddings over distributional semantic representations, supporting the hypothesis that they can better capture hierarchical lexical-semantic relationships than embeddings in the Euclidean space.

Semantic parsing over multiple knowledge bases enables a parser to exploit structural similarities of programs across the multiple domains. However, the fundamental challenge lies in obtaining high-quality annotations of (utterance, program) pairs across various domains needed for training such models. To overcome this, we propose a novel framework to build a unified multi-domain enabled semantic parser trained only with weak supervision (denotations). Weakly supervised training is particularly arduous as the program search space grows exponentially in a multi-domain setting. To solve this, we incorporate a multi-policy distillation mechanism in which we first train domain-specific semantic parsers (teachers) using weak supervision in the absence of the ground truth programs, followed by training a single unified parser (student) from the domain specific policies obtained from these teachers. The resultant semantic parser is not only compact but also generalizes better, and generates more accurate programs. It further does not require the user to provide a domain label while querying. On the standard Overnight dataset (containing multiple domains), we demonstrate that the proposed model improves performance by 20% in terms of denotation accuracy in comparison to baseline techniques.

Recent work by Zellers et al. (2018) introduced a new task of commonsense natural language inference: given an event description such as “A woman sits at a piano,” a machine must select the most likely followup: “She sets her fingers on the keys.” With the introduction of BERT, near human-level performance was reached. Does this mean that machines can perform human level commonsense inference? In this paper, we show that commonsense inference still proves difficult for even state-of-the-art models, by presenting HellaSwag, a new challenge dataset. Though its questions are trivial for humans (>95% accuracy), state-of-the-art models struggle (<48%). We achieve this via Adversarial Filtering (AF), a data collection paradigm wherein a series of discriminators iteratively select an adversarial set of machine-generated wrong answers. AF proves to be surprisingly robust. The key insight is to scale up the length and complexity of the dataset examples towards a critical ‘Goldilocks’ zone wherein generated text is ridiculous to humans, yet often misclassified by state-of-the-art models. Our construction of HellaSwag, and its resulting difficulty, sheds light on the inner workings of deep pretrained models. More broadly, it suggests a new path forward for NLP research, in which benchmarks co-evolve with the evolving state-of-the-art in an adversarial way, so as to present ever-harder challenges.

Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding. We present a supervised model for automatically identifying when one event is a subevent of another. Building on prior work, we introduce several novel features, in particular discourse and narrative features, that significantly improve upon prior state-of-the-art performance. Error analysis further demonstrates the utility of these features. We evaluate our model on the only two annotated corpora with event hierarchies: HiEve and the Intelligence Community corpus. No prior system has been evaluated on both corpora. Our model outperforms previous systems on both corpora, achieving 0.74 BLANC F1 on the Intelligence Community corpus and 0.70 F1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models.

We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.

We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding–based approaches that consider each sequence separately, our proposed framework utilizes both sequences within a single model by generating a sequence that has a given relationship with a source sequence. We further extend the cross-sentence generating framework to facilitate semi-supervised training. We also define novel semantic constraints that lead the decoder network to generate semantically plausible and diverse sequences. We demonstrate the effectiveness of the proposed model from quantitative and qualitative experiments, while achieving state-of-the-art results on semi-supervised natural language inference and paraphrase identification.

Link prediction and entailment graph induction are often treated as different problems. In this paper, we show that these two problems are actually complementary. We train a link prediction model on a knowledge graph of assertions extracted from raw text. We propose an entailment score that exploits the new facts discovered by the link prediction model, and then form entailment graphs between relations. We further use the learned entailments to predict improved link prediction scores. Our results show that the two tasks can benefit from each other. The new entailment score outperforms prior state-of-the-art results on a standard entialment dataset and the new link prediction scores show improvements over the raw link prediction scores.

We present a monolingual alignment system for long, sentence- or clause-level alignments, and demonstrate that systems designed for word- or short phrase-based alignment are ill-suited for these longer alignments. Our system is capable of aligning semantically similar spans of arbitrary length. We achieve significantly higher recall on aligning phrases of four or more words and outperform state-of-the- art aligners on the long alignments in the MSR RTE corpus.

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention-based feature embedding that captures both entity and relation features in any given entity’s neighborhood. Additionally, we also encapsulate relation clusters and multi-hop relations in our model. Our empirical study offers insights into the efficacy of our attention-based model and we show marked performance gains in comparison to state-of-the-art methods on all datasets.

In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three key features available for inter-sequence alignment: original point-wise features, previous aligned features, and contextual features while simplifying all the remaining components. We conduct experiments on four well-studied benchmark datasets across tasks of natural language inference, paraphrase identification and answer selection. The performance of our model is on par with the state-of-the-art on all datasets with much fewer parameters and the inference speed is at least 6 times faster compared with similarly performed ones.

For several natural language processing (NLP) tasks, span representation design is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.

Political debates offer a rare opportunity for citizens to compare the candidates’ positions on the most controversial topics of the campaign. Thus they represent a natural application scenario for Argument Mining. As existing research lacks solid empirical investigation of the typology of argument components in political debates, we fill this gap by proposing an Argument Mining approach to political debates. We address this task in an empirical manner by annotating 39 political debates from the last 50 years of US presidential campaigns, creating a new corpus of 29k argument components, labeled as premises and claims. We then propose two tasks: (1) identifying the argumentative components in such debates, and (2) classifying them as premises and claims. We show that feature-rich SVM learners and Neural Network architectures outperform standard baselines in Argument Mining over such complex data. We release the new corpus USElecDeb60To16 and the accompanying software under free licenses to the research community.

Attention-based neural models were employed to detect the different aspects and sentiment polarities of the same target in targeted aspect-based sentiment analysis (TABSA). However, existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA. This may result in targets or aspects having the same vector representations in different contexts and losing the context-dependent information. To address this problem, we propose a novel method to refine the embeddings of targets and aspects. Such pivotal embedding refinement utilizes a sparse coefficient vector to adjust the embeddings of target and aspect from the context. Hence the embeddings of targets and aspects can be refined from the highly correlative words instead of using context-independent or randomly initialized vectors. Experiment results on two benchmark datasets show that our approach yields the state-of-the-art performance in TABSA task.

In sentiment detection, the natural language processing community has focused on determining holders, facets, and valences, but has paid little attention to the reasons for sentiment decisions. Our work considers human motives as the driver for human sentiments and addresses the problem of motive detection as the first step. Following a study in psychology, we define six basic motives that cover a wide range of topics appearing in review texts, annotate 1,600 texts in restaurant and laptop domains with the motives, and report the performance of baseline methods on this new dataset. We also show that cross-domain transfer learning boosts detection performance, which indicates that these universal motives exist across different domains.