ACL 2019 论文列表

We describe a multi-task learning approach to train a Neural Machine Translation (NMT) model with a Relevance-based Auxiliary Task (RAT) for search query translation. The translation process for Cross-lingual Information Retrieval (CLIR) task is usually treated as a black box and it is performed as an independent step. However, an NMT model trained on sentence-level parallel data is not aware of the vocabulary distribution of the retrieval corpus. We address this problem and propose a multi-task learning architecture that achieves 16% improvement over a strong baseline on Italian-English query-document dataset. We show using both quantitative and qualitative analysis that our model generates balanced and precise translations with the regularization effect it achieves from multi-task learning paradigm.

While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method proposed by Zhang et al. (2017) and discover that it cannot reliably tell whether a given sentence occurs in the input paragraph or not. We formulate a sentence content task to probe for this basic linguistic property and find that even a much simpler bag-of-words method has no trouble solving it. This result motivates us to replace the reconstruction-based objective of Zhang et al. (2017) with our sentence content probe objective in a semi-supervised setting. Despite its simplicity, our objective improves over paragraph reconstruction in terms of (1) downstream classification accuracies on benchmark datasets, (2) faster training, and (3) better generalization ability.

To address the lack of comparative evaluation of Human-in-the-Loop Topic Modeling (HLTM) systems, we implement and evaluate three contrasting HLTM modeling approaches using simulation experiments. These approaches extend previously proposed frameworks, including constraints and informed prior-based methods. Users should have a sense of control in HLTM systems, so we propose a control metric to measure whether refinement operations’ results match users’ expectations. Informed prior-based methods provide better control than constraints, but constraints yield higher quality topics.

We consider Large-Scale Multi-Label Text Classification (LMTC) in the legal domain. We release a new dataset of 57k legislative documents from EUR-LEX, annotated with ∼4.3k EUROVOC labels, which is suitable for LMTC, few- and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with label-wise attention perform better than other current state of the art methods. Domain-specific WORD2VEC and context-sensitive ELMO embeddings further improve performance. We also find that considering only particular zones of the documents is sufficient. This allows us to bypass BERT’s maximum text length limit and fine-tune BERT, obtaining the best results in all but zero-shot learning cases.

In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description. A large benchmark dataset, called Numeracy-600K, is provided for the novel task. We explore several neural network models including CNN, GRU, BiGRU, CRNN, CNN-capsule, GRU-capsule, and BiGRU-capsule in the experiments. The results show that the BiGRU model gets the best micro-averaged F1 score of 80.16%, and the GRU-capsule model gets the best macro-averaged F1 score of 64.71%. Besides discussing the challenges through comprehensive experiments, we also present an important application scenario, i.e., detecting exaggerated information, for the task.

The PAN series of shared tasks is well known for its continuous and high quality research in the field of digital text forensics. Among others, PAN contributions include original corpora, tailored benchmarks, and standardized experimentation platforms. In this paper we review, theoretically and practically, the authorship verification task and conclude that the underlying experiment design cannot guarantee pushing forward the state of the art—in fact, it allows for top benchmarking with a surprisingly straightforward approach. In this regard, we present a “Basic and Fairly Flawed” (BAFF) authorship verifier that is on a par with the best approaches submitted so far, and that illustrates sources of bias that should be eliminated. We pinpoint these sources in the evaluation chain and present a refined authorship corpus as effective countermeasure.

Multi-Label Hierarchical Text Classification (MLHTC) is the task of categorizing documents into one or more topics organized in an hierarchical taxonomy. MLHTC can be formulated by combining multiple binary classification problems with an independent classifier for each category. We propose a novel transfer learning based strategy, HTrans, where binary classifiers at lower levels in the hierarchy are initialized using parameters of the parent classifier and fine-tuned on the child category classification task. In HTrans, we use a Gated Recurrent Unit (GRU)-based deep learning architecture coupled with attention. Compared to binary classifiers trained from scratch, our HTrans approach results in significant improvements of 1% on micro-F1 and 3% on macro-F1 on the RCV1 dataset. Our experiments also show that binary classifiers trained from scratch are significantly better than single multi-label models.

Identifying the relationship between two articles, e.g., whether two articles published from different sources describe the same breaking news, is critical to many document understanding tasks. Existing approaches for modeling and matching sentence pairs do not perform well in matching longer documents, which embody more complex interactions between the enclosed entities than a sentence does. To model article pairs, we propose the Concept Interaction Graph to represent an article as a graph of concepts. We then match a pair of articles by comparing the sentences that enclose the same concept vertex through a series of encoding techniques, and aggregate the matching signals through a graph convolutional network. To facilitate the evaluation of long article matching, we have created two datasets, each consisting of about 30K pairs of breaking news articles covering diverse topics in the open domain. Extensive evaluations of the proposed methods on the two datasets demonstrate significant improvements over a wide range of state-of-the-art methods for natural language matching.

Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in scarce data setting by forcing model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a tradeoff on the original task; ii) incorporating prior helps model performance in scarce data settings.

Automatic summarization is typically treated as a 1-to-1 mapping from document to summary. Documents such as news articles, however, are structured and often cover multiple topics or aspects; and readers may be interested in only some of them. We tackle the task of aspect-based summarization, where, given a document and a target aspect, our models generate a summary centered around the aspect. We induce latent document structure jointly with an abstractive summarization objective, and train our models in a scalable synthetic setup. In addition to improvements in summarization over topic-agnostic baselines, we demonstrate the benefit of the learnt document structure: we show that our models (a) learn to accurately segment documents by aspect; (b) can leverage the structure to produce both abstractive and extractive aspect-based summaries; and (c) that structure is particularly advantageous for summarizing long documents. All results transfer from synthetic training documents to natural news articles from CNN/Daily Mail and RCV1.

We introduce a novel semantic parsing task based on Discourse Representation Theory (DRT; Kamp and Reyle 1993). Our model operates over Discourse Representation Tree Structures which we formally define for sentences and documents. We present a general framework for parsing discourse structures of arbitrary length and granularity. We achieve this with a neural model equipped with a supervised hierarchical attention mechanism and a linguistically-motivated copy strategy. Experimental results on sentence- and document-level benchmarks show that our model outperforms competitive baselines by a wide margin.

Single document summarization has enjoyed renewed interest in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. In this paper we develop an unsupervised approach arguing that it is unrealistic to expect large-scale and high-quality training data to be available or created for different types of summaries, domains, or languages. We revisit a popular graph-based ranking algorithm and modify how node (aka sentence) centrality is computed in two ways: (a) we employ BERT, a state-of-the-art neural representation learning model to better capture sentential meaning and (b) we build graphs with directed edges arguing that the contribution of any two nodes to their respective centrality is influenced by their relative position in a document. Experimental results on three news summarization datasets representative of different languages and writing styles show that our approach outperforms strong baselines by a wide margin.

We present a fully automated workflow for phylogenetic reconstruction on large datasets, consisting of two novel methods, one for fast detection of cognates and one for fast Bayesian phylogenetic inference. Our results show that the methods take less than a few minutes to process language families that have so far required large amounts of time and computational power. Moreover, the cognates and the trees inferred from the method are quite close, both to gold standard cognate judgments and to expert language family trees. Given its speed and ease of application, our framework is specifically useful for the exploration of very large datasets in historical linguistics.

Graphics Processing Units (GPUs) are commonly used to train and evaluate neural networks efficiently. While previous work in deep learning has focused on accelerating operations on dense matrices/tensors on GPUs, efforts have concentrated on operations involving sparse data structures. Operations using sparse structures are common in natural language models at the input and output layers, because these models operate on sequences over discrete alphabets. We present two new GPU algorithms: one at the input layer, for multiplying a matrix by a few-hot vector (generalizing the more common operation of multiplication by a one-hot vector) and one at the output layer, for a fused softmax and top-N selection (commonly used in beam search). Our methods achieve speedups over state-of-the-art parallel GPU baselines of up to 7x and 50x, respectively. We also illustrate how our methods scale on different GPU architectures.

Multilingual individuals code switch between languages as a part of a complex communication process. However, most computational studies have examined only one or a handful of contextual factors predictive of switching. Here, we examine Naija-English code switching in a rich contextual environment to understand the social and topical factors eliciting a switch. We introduce a new corpus of 330K articles and accompanying 389K comments labeled for code switching behavior. In modeling whether a comment will switch, we show that topic-driven variation, tribal affiliation, emotional valence, and audience design all play complementary roles in behavior.

In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT). Specifically, we show that a shallow sentential context extracted from the top encoder layer only, can improve translation performance via contextualizing the encoding representations of individual words. Next, we introduce a deep sentential context, which aggregates the sentential context representations from all of the internal layers of the encoder to form a more comprehensive context representation. Experimental results on the WMT14 English-German and English-French benchmarks show that our model consistently improves performance over the strong Transformer model, demonstrating the necessity and effectiveness of exploiting sentential context for NMT.

While neural machine translation (NMT) has achieved remarkable success, NMT systems are prone to make word omission errors. In this work, we propose a contrastive learning approach to reducing word omission errors in NMT. The basic idea is to enable the NMT model to assign a higher probability to a ground-truth translation and a lower probability to an erroneous translation, which is automatically constructed from the ground-truth translation by omitting words. We design different types of negative examples depending on the number of omitted words, word frequency, and part of speech. Experiments on Chinese-to-English, German-to-English, and Russian-to-English translation tasks show that our approach is effective in reducing word omission errors and achieves better translation performance than three baseline methods.

Conversational machine reading comprehension (CMRC) extends traditional single-turn machine reading comprehension (MRC) by multi-turn interactions, which requires machines to consider the history of conversation. Most of models simply combine previous questions for conversation understanding and only employ recurrent neural networks (RNN) for reasoning. To comprehend context profoundly and efficiently from different perspectives, we propose a novel neural network model, Multi-perspective Convolutional Cube (MCˆ2). We regard each conversation as a cube. 1D and 2D convolutions are integrated with RNN in our model. To avoid models previewing the next turn of conversation, we also extend causal convolution partially to 2D. Experiments on the Conversational Question Answering (CoQA) dataset show that our model achieves state-of-the-art results.

Although current evaluation of question-answering systems treats predictions in isolation, we need to consider the relationship between predictions to measure true understanding. A model should be penalized for answering “no” to “Is the rose red?” if it answers “red” to “What color is the rose?”. We propose a method to automatically extract such implications for instances from two QA datasets, VQA and SQuAD, which we then use to evaluate the consistency of models. Human evaluation shows these generated implications are well formed and valid. Consistency evaluation provides crucial insights into gaps in existing models, while retraining with implication-augmented data improves consistency on both synthetic and human-generated implications.