EMNLP 2021 论文列表

With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in F1 of up to 28% over the baseline bilingual word aligner in different datasets.

Although grammatical error correction (GEC) has achieved good performance on texts written by learners of English as a second language, performance on low error density domains where texts are written by English speakers of varying levels of proficiency can still be improved. In this paper, we propose a contrastive learning approach to encourage the GEC model to assign a higher probability to a correct sentence while reducing the probability of incorrect sentences that the model tends to generate, so as to improve the accuracy of the model. Experimental results show that our approach significantly improves the performance of GEC models in low error density domains, when evaluated on the benchmark CWEB dataset.

We propose the first general-purpose gradient-based adversarial attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix, hence enabling gradient-based optimization. We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks, outperforming prior work in terms of adversarial success rate with matching imperceptibility as per automated and human evaluation. Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.

Neural abstractive summarization systems have gained significant progress in recent years. However, abstractive summarization often produce inconsisitent statements or false facts. How to automatically generate highly abstract yet factually correct summaries? In this paper, we proposed an efficient weak-supervised adversarial data augmentation approach to form the factual consistency dataset. Based on the artificial dataset, we train an evaluation model that can not only make accurate and robust factual consistency discrimination but is also capable of making interpretable factual errors tracing by backpropagated gradient distribution on token embeddings. Experiments and analysis conduct on public annotated summarization and factual consistency datasets demonstrate our approach effective and reasonable.

Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines.

A key problem in multi-task learning (MTL) research is how to select high-quality auxiliary tasks automatically. This paper presents GradTS, an automatic auxiliary task selection method based on gradient calculation in Transformer-based models. Compared to AUTOSEM, a strong baseline method, GradTS improves the performance of MT-DNN with a bert-base-cased backend model, from 0.33% to 17.93% on 8 natural language understanding (NLU) tasks in the GLUE benchmarks. GradTS is also time-saving since (1) its gradient calculations are based on single-task experiments and (2) the gradients are re-used without additional experiments when the candidate task set changes. On the 8 GLUE classification tasks, for example, GradTS costs on average 21.32% less time than AUTOSEM with comparable GPU consumption. Further, we show the robustness of GradTS across various task settings and model selections, e.g. mixed objectives among candidate tasks. The efficiency and efficacy of GradTS in these case studies illustrate its general applicability in MTL research without requiring manual task filtering or costly parameter tuning.

This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data augmentation protocol called “good-enough example extrapolation” (GE3). GE3 is lightweight and has no hyperparameters. Applied to three text classification datasets for various data imbalance scenarios, GE3 improves performance more than upsampling and other hidden-space data augmentation methods.

While day-to-day questions come with a variety of answer types, the current question-answering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GooAQ, a large-scale dataset with a variety of answer types. This dataset contains over 5 million questions and 3 million answers collected from Google. GooAQ questions are collected semi-automatically from the Google search engine using its autocomplete feature. This results in naturalistic questions of practical interest that are nonetheless short and expressed using simple language. GooAQ answers are mined from Google’s responses to our collected questions, specifically from the answer boxes in the search results. This yields a rich space of answer types, containing both textual answers (short and long) as well as more structured ones such as collections. We benchmark T5 models on GooAQ and observe that: (a) in line with recent work, LM’s strong performance on GooAQ’s short-answer questions heavily benefit from annotated data; however, (b) their quality in generating coherent and accurate responses for questions requiring long responses (such as ‘how’ and ‘why’ questions) is less reliant on observing annotated data and mainly supported by their pre-training. We release GooAQ to facilitate further research on improving QA with diverse response types.

Sememes are defined as the atomic units to describe the semantic meaning of concepts. Due to the difficulty of manually annotating sememes and the inconsistency of annotations between experts, the lexical sememe prediction task has been proposed. However, previous methods heavily rely on word or character embeddings, and ignore the fine-grained information. In this paper, we propose a novel pre-training method which is designed to better incorporate the internal information of Chinese character. The Glyph enhanced Chinese Character representation (GCC) is used to assist sememe prediction. We experiment and evaluate our model on HowNet, which is a famous sememe knowledge base. The experimental results show that our method outperforms existing non-external information models.

Evaluation metrics are a key ingredient for progress of text generation systems. In recent years, several BERT-based evaluation metrics have been proposed (including BERTScore, MoverScore, BLEURT, etc.) which correlate much better with human assessment of text generation quality than BLEU or ROUGE, invented two decades ago. However, little is known what these metrics, which are based on black-box language model representations, actually capture (it is typically assumed they model semantic similarity). In this work, we use a simple regression based global explainability technique to disentangle metric scores along linguistic factors, including semantics, syntax, morphology, and lexical overlap. We show that the different metrics capture all aspects to some degree, but that they are all substantially sensitive to lexical overlap, just like BLEU and ROUGE. This exposes limitations of these novelly proposed metrics, which we also highlight in an adversarial test scenario.

Abstractive dialogue summarization suffers from a lots of factual errors, which are due to scattered salient elements in the multi-speaker information interaction process. In this work, we design a heterogeneous semantic slot graph with a slot-level mask cross-attention to enhance the slot features for more correct summarization. We also propose a slot-driven beam search algorithm in the decoding process to give priority to generating salient elements in a limited length by “filling-in-the-blanks”. Besides, an adversarial contrastive learning assisting the training process is introduced to alleviate the exposure bias. Experimental performance on different types of factual errors shows the effectiveness of our methods and human evaluation further verifies the results..

Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words – either through masking or next sentence prediction – and has no knowledge of lexical, syntactic or semantic information beyond what it picks up through unsupervised pre-training. We propose a novel method to explicitly inject linguistic information in the form of word embeddings into any layer of a pre-trained BERT. When injecting counter-fitted and dependency-based embeddings, the performance improvements on multiple semantic similarity datasets indicate that such information is beneficial and currently missing from the original model. Our qualitative analysis shows that counter-fitted embedding injection is particularly beneficial, with notable improvements on examples that require synonym resolution.

Query Rewriting (QR) is proposed to solve the problem of the word mismatch between queries and documents in Web search. Existing approaches usually model QR with an end-to-end sequence-to-sequence (seq2seq) model. The state-of-the-art Transformer-based models can effectively learn textual semantics from user session logs, but they often ignore users’ geographic location information that is crucial for the Point-of-Interest (POI) search of map services. In this paper, we proposed a pre-training model, called Geo-BERT, to integrate semantics and geographic information in the pre-trained representations of POIs. Firstly, we simulate POI distribution in the real world as a graph, in which nodes represent POIs and multiple geographic granularities. Then we use graph representation learning methods to get geographic representations. Finally, we train a BERT-like pre-training model with text and POIs’ graph embeddings to get an integrated representation of both geographic and semantic information, and apply it in the QR of POI search. The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services.

Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.

Style transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages generic resources, and without using any task-specific parallel (source–target) data outperforms existing unsupervised approaches on the two most popular style transfer tasks: formality transfer and polarity swap. In practice, we adopt a multi-step procedure which builds on a generic pre-trained sequence-to-sequence model (BART). First, we strengthen the model’s ability to rewrite by further pre-training BART on both an existing collection of generic paraphrases, as well as on synthetic pairs created using a general-purpose lexical resource. Second, through an iterative back-translation approach, we train two models, each in a transfer direction, so that they can provide each other with synthetically generated pairs, dynamically in the training process. Lastly, we let our best resulting model generate static synthetic pairs to be used in a supervised training regime. Besides methodology and state-of-the-art results, a core contribution of this work is a reflection on the nature of the two tasks we address, and how their differences are highlighted by their response to our approach.

Previous neural Seq2Seq models have shown the effectiveness for jointly extracting relation triplets. However, most of these models suffer from incompletion and disorder problems when they extract multi-token entities from input sentences. To tackle these problems, we propose a generative, multi-task learning framework, named GenerativeRE. We firstly propose a special entity labelling method on both input and output sequences. During the training stage, GenerativeRE fine-tunes the pre-trained generative model and learns the special entity labels simultaneously. During the inference stage, we propose a novel copy mechanism equipped with three mask strategies, to generate the most probable tokens by diminishing the scope of the model decoder. Experimental results show that our model achieves 4.6% and 0.9% F1 score improvements over the current state-of-the-art methods in the NYT24 and NYT29 benchmark datasets respectively.

Compositional reasoning tasks such as multi-hop question answering require models to learn how to make latent decisions using only weak supervision from the final answer. Crowdsourced datasets gathered for these tasks, however, often contain only a slice of the underlying task distribution, which can induce unanticipated biases such as shallow word overlap between the question and context. Recent works have shown that discriminative training results in models that exploit these underlying biases to achieve a better held-out performance, without learning the right way to reason. We propose a generative context selection model for multi-hop QA that reasons about how the given question could have been generated given a context pair and not just independent contexts. We show that on HotpotQA, while being comparable to the state-of-the-art answering performance, our proposed generative passage selection model has a better performance (4.9% higher than baseline) on adversarial held-out set which tests robustness of model’s multi-hop reasoning capabilities.

Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains. The task is characterized by the shared slots between domains. As the scenario gets more complex, the out-of-vocabulary problem also becomes severer. Current models are not satisfactory for solving the challenges of ontology integration between domains and out-of-vocabulary problems. To address the problem, we explore the hierarchical semantic of ontology and enhance the interrelation between slots with masked hierarchical attention. In state value decoding stage, we solve the out-of-vocabulary problem by combining generation method and extraction method together. We evaluate the performance of our model on two representative datasets, MultiWOZ in English and CrossWOZ in Chinese. The results show that our model yields a significant performance gain over current state-of-the-art state tracking model and it is more robust to out-of-vocabulary problem compared with other methods.

Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing answers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.