ACL 2020 论文列表

Training the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters on all non-target tasks then fine-tunes on the target task. However, fine-tuning distinguishes tasks from the parameter perspective but ignores the model-structure perspective, resulting in similar dialogue models for different tasks. In this paper, we propose an algorithm that can customize a unique dialogue model for each task in the few-shot setting. In our approach, each dialogue model consists of a shared module, a gating module, and a private module. The first two modules are shared among all the tasks, while the third one will differentiate into different network structures to better capture the characteristics of the corresponding task. The extensive experiments on two datasets show that our method outperforms all the baselines in terms of task consistency, response quality, and diversity.

Maintaining a consistent personality in conversations is quite natural for human beings, but is still a non-trivial task for machines. The persona-based dialogue generation task is thus introduced to tackle the personality-inconsistent problem by incorporating explicit persona text into dialogue generation models. Despite the success of existing persona-based models on generating human-like responses, their one-stage decoding framework can hardly avoid the generation of inconsistent persona words. In this work, we introduce a three-stage framework that employs a generate-delete-rewrite mechanism to delete inconsistent words from a generated response prototype and further rewrite it to a personality-consistent one. We carry out evaluations by both human and automatic metrics. Experiments on the Persona-Chat dataset show that our approach achieves good performance.

Generative dialogue systems tend to produce generic responses, which often leads to boring conversations. For alleviating this issue, Recent studies proposed to retrieve and introduce knowledge facts from knowledge graphs. While this paradigm works to a certain extent, it usually retrieves knowledge facts only based on the entity word itself, without considering the specific dialogue context. Thus, the introduction of the context-irrelevant knowledge facts can impact the quality of generations. To this end, this paper proposes a novel commonsense knowledge-aware dialogue generation model, ConKADI. We design a Felicitous Fact mechanism to help the model focus on the knowledge facts that are highly relevant to the context; furthermore, two techniques, Context-Knowledge Fusion and Flexible Mode Fusion are proposed to facilitate the integration of the knowledge in the ConKADI. We collect and build a large-scale Chinese dataset aligned with the commonsense knowledge for dialogue generation. Extensive evaluations over both an open-released English dataset and our Chinese dataset demonstrate that our approach ConKADI outperforms the state-of-the-art approach CCM, in most experiments.

Affective tasks such as sentiment analysis, emotion classification, and sarcasm detection have been popular in recent years due to an abundance of user-generated data, accurate computational linguistic models, and a broad range of relevant applications in various domains. At the same time, many studies have highlighted the importance of text preprocessing, as an integral step to any natural language processing prediction model and downstream task. While preprocessing in affective systems is well-studied, preprocessing in word vector-based models applied to affective systems, is not. To address this limitation, we conduct a comprehensive analysis of the role of preprocessing techniques in affective analysis based on word vector models. Our analysis is the first of its kind and provides useful insights of the importance of each preprocessing technique when applied at the training phase, commonly ignored in pretrained word vector models, and/or at the downstream task phase.

We present OpinionDigest, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. At summarization time, we merge extractions from multiple reviews and select the most popular ones. The selected opinions are used as input to the trained Transformer model, which verbalizes them into an opinion summary. OpinionDigest can also generate customized summaries, tailored to specific user needs, by filtering the selected opinions according to their aspect and/or sentiment. Automatic evaluation on Yelp data shows that our framework outperforms competitive baselines. Human studies on two corpora verify that OpinionDigest produces informative summaries and shows promising customization capabilities.

This paper studies the task of comparative preference classification (CPC). Given two entities in a sentence, our goal is to classify whether the first (or the second) entity is preferred over the other or no comparison is expressed at all between the two entities. Existing works either do not learn entity-aware representations well and fail to deal with sentences involving multiple entity pairs or use sequential modeling approaches that are unable to capture long-range dependencies between the entities. Some also use traditional machine learning approaches that do not generalize well. This paper proposes a novel Entity-aware Dependency-based Deep Graph Attention Network (ED-GAT) that employs a multi-hop graph attention over a dependency graph sentence representation to leverage both the semantic information from word embeddings and the syntactic information from the dependency graph to solve the problem. Empirical evaluation shows that the proposed model achieves the state-of-the-art performance in comparative preference classification.

We present an efficient annotation framework for argument quality, a feature difficult to be measured reliably as per previous work. A stochastic transitivity model is combined with an effective sampling strategy to infer high-quality labels with low effort from crowdsourced pairwise judgments. The model’s capabilities are showcased by compiling Webis-ArgQuality-20, an argument quality corpus that comprises scores for rhetorical, logical, dialectical, and overall quality inferred from a total of 41,859 pairwise judgments among 1,271 arguments. With up to 93% cost savings, our approach significantly outperforms existing annotation procedures. Furthermore, novel insight into argument quality is provided through statistical analysis, and a new aggregation method to infer overall quality from individual quality dimensions is proposed.

Recent neural network models have achieved impressive performance on sentiment classification in English as well as other languages. Their success heavily depends on the availability of a large amount of labeled data or parallel corpus. In this paper, we investigate an extreme scenario of cross-lingual sentiment classification, in which the low-resource language does not have any labels or parallel corpus. We propose an unsupervised cross-lingual sentiment classification model named multi-view encoder-classifier (MVEC) that leverages an unsupervised machine translation (UMT) system and a language discriminator. Unlike previous language model (LM) based fine-tuning approaches that adjust parameters solely based on the classification error on training data, we employ the encoder-decoder framework of a UMT as a regularization component on the shared network parameters. In particular, the cross-lingual encoder of our model learns a shared representation, which is effective for both reconstructing input sentences of two languages and generating more representative views from the input for classification. Extensive experiments on five language pairs verify that our model significantly outperforms other models for 8/11 sentiment classification tasks.

In online debates, users express different levels of agreement/disagreement with one another’s arguments and ideas. Often levels of agreement/disagreement are implicit in the text, and must be predicted to analyze collective opinions. Existing stance detection methods predict the polarity of a post’s stance toward a topic or post, but don’t consider the stance’s degree of intensity. We introduce a new research problem, stance polarity and intensity prediction in response relationships between posts. This problem is challenging because differences in stance intensity are often subtle and require nuanced language understanding. Cyber argumentation research has shown that incorporating both stance polarity and intensity data in online debates leads to better discussion analysis. We explore five different learning models: Ridge-M regression, Ridge-S regression, SVR-RF-R, pkudblab-PIP, and T-PAN-PIP for predicting stance polarity and intensity in argumentation. These models are evaluated using a new dataset for stance polarity and intensity prediction collected using a cyber argumentation platform. The SVR-RF-R model performs best for prediction of stance polarity with an accuracy of 70.43% and intensity with RMSE of 0.596. This work is the first to train models for predicting a post’s stance polarity and intensity in one combined value in cyber argumentation with reasonably good accuracy.

In this paper, we present the first comprehensive categorization of essential commonsense knowledge for answering the Winograd Schema Challenge (WSC). For each of the questions, we invite annotators to first provide reasons for making correct decisions and then categorize them into six major knowledge categories. By doing so, we better understand the limitation of existing methods (i.e., what kind of knowledge cannot be effectively represented or inferred with existing methods) and shed some light on the commonsense knowledge that we need to acquire in the future for better commonsense reasoning. Moreover, to investigate whether current WSC models can understand the commonsense or they simply solve the WSC questions based on the statistical bias of the dataset, we leverage the collected reasons to develop a new task called WinoWhy, which requires models to distinguish plausible reasons from very similar but wrong reasons for all WSC questions. Experimental results prove that even though pre-trained language representation models have achieved promising progress on the original WSC dataset, they are still struggling at WinoWhy. Further experiments show that even though supervised models can achieve better performance, the performance of these models can be sensitive to the dataset distribution. WinoWhy and all codes are available at: https://github.com/HKUST-KnowComp/WinoWhy.

We present STARC (Structured Annotations for Reading Comprehension), a new annotation framework for assessing reading comprehension with multiple choice questions. Our framework introduces a principled structure for the answer choices and ties them to textual span annotations. The framework is implemented in OneStopQA, a new high-quality dataset for evaluation and analysis of reading comprehension in English. We use this dataset to demonstrate that STARC can be leveraged for a key new application for the development of SAT-like reading comprehension materials: automatic annotation quality probing via span ablation experiments. We further show that it enables in-depth analyses and comparisons between machine and human reading comprehension behavior, including error distributions and guessing ability. Our experiments also reveal that the standard multiple choice dataset in NLP, RACE, is limited in its ability to measure reading comprehension. 47% of its questions can be guessed by machines without accessing the passage, and 18% are unanimously judged by humans as not having a unique correct answer. OneStopQA provides an alternative test set for reading comprehension which alleviates these shortcomings and has a substantially higher human ceiling performance.

Empirical research in Natural Language Processing (NLP) has adopted a narrow set of principles for assessing hypotheses, relying mainly on p-value computation, which suffers from several known issues. While alternative proposals have been well-debated and adopted in other fields, they remain rarely discussed or used within the NLP community. We address this gap by contrasting various hypothesis assessment techniques, especially those not commonly used in the field (such as evaluations based on Bayesian inference). Since these statistical techniques differ in the hypotheses they can support, we argue that practitioners should first decide their target hypothesis before choosing an assessment method. This is crucial because common fallacies, misconceptions, and misinterpretation surrounding hypothesis assessment methods often stem from a discrepancy between what one would like to claim versus what the method used actually assesses. Our survey reveals that these issues are omnipresent in the NLP research community. As a step forward, we provide best practices and guidelines tailored to NLP research, as well as an easy-to-use package for Bayesian assessment of hypotheses, complementing existing tools.

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts. Then, multi-task learning between the utterance prediction and the token span prediction is applied to fine-tune for span-based question answering (QA). Our approach is evaluated on the FriendsQA dataset and shows improvements of 3.8% and 1.4% over the two state-of-the-art transformer models, BERT and RoBERTa, respectively.

Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents their use in applications requiring the classification of a large set of candidates. While previous works have investigated approaches to reduce model size, relatively little attention has been paid to techniques to improve batch throughput during inference. In this paper, we introduce the Cascade Transformer, a simple yet effective technique to adapt transformer-based models into a cascade of rankers. Each ranker is used to prune a subset of candidates in a batch, thus dramatically increasing throughput at inference time. Partial encodings from the transformer model are shared among rerankers, providing further speed-up. When compared to a state-of-the-art transformer model, our approach reduces computation by 37% with almost no impact on accuracy, as measured on two English Question Answering datasets.

To avoid giving wrong answers, question answering (QA) models need to know when to abstain from answering. Moreover, users often ask questions that diverge from the model’s training data, making errors more likely and thus abstention more critical. In this work, we propose the setting of selective question answering under domain shift, in which a QA model is tested on a mixture of in-domain and out-of-domain data, and must answer (i.e., not abstain on) as many questions as possible while maintaining high accuracy. Abstention policies based solely on the model’s softmax probabilities fare poorly, since models are overconfident on out-of-domain inputs. Instead, we train a calibrator to identify inputs on which the QA model errs, and abstain when it predicts an error is likely. Crucially, the calibrator benefits from observing the model’s behavior on out-of-domain data, even if from a different domain than the test data. We combine this method with a SQuAD-trained QA model and evaluate on mixtures of SQuAD and five other QA datasets. Our method answers 56% of questions while maintaining 80% accuracy; in contrast, directly using the model’s probabilities only answers 48% at 80% accuracy.

We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction. SCDE is a human created sentence cloze dataset, collected from public school English examinations. Our task requires a model to fill up multiple blanks in a passage from a shared candidate set with distractors designed by English teachers. Experimental results demonstrate that this task requires the use of non-local, discourse-level context beyond the immediate sentence neighborhood. The blanks require joint solving and significantly impair each other’s context. Furthermore, through ablations, we show that the distractors are of high quality and make the task more challenging. Our experiments show that there is a significant performance gap between advanced models (72%) and humans (87%), encouraging future models to bridge this gap.

We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant supervision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multi-objective model can efficiently combine the advantages of multiple assumptions and outperform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries.

Automatic question generation (QG) has shown promise as a source of synthetic training data for question answering (QA). In this paper we ask: Is textual diversity in QG beneficial for downstream QA? Using top-p nucleus sampling to derive samples from a transformer-based question generator, we show that diversity-promoting QG indeed provides better QA training than likelihood maximization approaches such as beam search. We also show that standard QG evaluation metrics such as BLEU, ROUGE and METEOR are inversely correlated with diversity, and propose a diversity-aware intrinsic measure of overall QG quality that correlates well with extrinsic evaluation on QA.

Many natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model. Improving the global consistency of predictions, our approach achieves large improvements over previous methods in a variety of question answering (QA) tasks, including multiple-choice qualitative reasoning, cause-effect reasoning, and extractive machine reading comprehension. In particular, our method significantly improves the performance of RoBERTa-based models by 1-5% across datasets. We advance state of the art by around 5-8% on WIQA and QuaRel and reduce consistency violations by 58% on HotpotQA. We further demonstrate that our approach can learn effectively from limited data.