EMNLP 2020 论文列表

We propose Grounded Adaptation for Zeroshot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified through execution. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.

Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge. They suggest that it is promising to use PTLMs as “neural knowledge bases” via predicting masked words. Surprisingly, we find that this may not work for numerical commonsense knowledge (e.g., a bird usually has two legs). In this paper, we investigate whether and to what extent we can induce numerical commonsense knowledge from PTLMs as well as the robustness of this process. In this paper, we investigate whether and to what extent we can induce numerical commonsense knowledge from PTLMs as well as the robustness of this process. To study this, we introduce a novel probing task with a diagnostic dataset, NumerSense, containing 13.6k masked-word-prediction probes (10.5k for fine-tuning and 3.1k for testing). Our analysis reveals that: (1) BERT and its stronger variant RoBERTa perform poorly on the diagnostic dataset prior to any fine-tuning; (2) fine-tuning with distant supervision brings some improvement; (3) the best supervised model still performs poorly as compared to human performance (54.06% vs. 96.3% in accuracy).

Pre-trained language models (LMs) may perpetuate biases originating in their training corpus to downstream models. We focus on artifacts associated with the representation of given names (e.g., Donald), which, depending on the corpus, may be associated with specific entities, as indicated by next token prediction (e.g., Trump). While helpful in some contexts, grounding happens also in under-specified or inappropriate contexts. For example, endings generated for ‘Donald is a’ substantially differ from those of other names, and often have more-than-average negative sentiment. We demonstrate the potential effect on downstream tasks with reading comprehension probes where name perturbation changes the model answers. As a silver lining, our experiments suggest that additional pre-training on different corpora may mitigate this bias.

In recent years, pre-trained Transformers have dominated the majority of NLP benchmark tasks. Many variants of pre-trained Transformers have kept breaking out, and most focus on designing different pre-training objectives or variants of self-attention. Embedding the position information in the self-attention mechanism is also an indispensable factor in Transformers however is often discussed at will. Hence, we carry out an empirical study on position embedding of mainstream pre-trained Transformers mainly focusing on two questions: 1) Do position embeddings really learn the meaning of positions? 2) How do these different learned position embeddings affect Transformers for NLP tasks? This paper focuses on providing a new insight of pre-trained position embeddings by feature-level analysis and empirical experiments on most of iconic NLP tasks. It is believed that our experimental results can guide the future works to choose the suitable positional encoding function for specific tasks given the application property.

We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data induce generalizable structural features that LSTMs can use for natural language. We find that training on non-linguistic data with latent structure (MIDI music or Java code) improves test performance on natural language, despite no overlap in surface form or vocabulary. To pinpoint the kinds of abstract structure that models may be encoding to lead to this improvement, we run similar experiments with two artificial parentheses languages: one which has a hierarchical recursive structure, and a control which has paired tokens but no recursion. Surprisingly, training a model on either of these artificial languages leads the same substantial gains when testing on natural language. Further experiments on transfer between natural languages controlling for vocabulary overlap show that zero-shot performance on a test language is highly correlated with typological syntactic similarity to the training language, suggesting that representations induced by pre-training correspond to the cross-linguistic syntactic properties. Our results provide insights into the ways that neural models represent abstract syntactic structure, and also about the kind of structural inductive biases which allow for natural language acquisition.

While behaviors of pretrained language models (LMs) have been thoroughly examined, what happened during pretraining is rarely studied. We thus investigate the developmental process from a set of randomly initialized parameters to a totipotent language model, which we refer to as the embryology of a pretrained language model. Our results show that ALBERT learns to reconstruct and predict tokens of different parts of speech (POS) in different learning speeds during pretraining. We also find that linguistic knowledge and world knowledge do not generally improve as pretraining proceeds, nor do downstream tasks’ performance. These findings suggest that knowledge of a pretrained model varies during pretraining, and having more pretrain steps does not necessarily provide a model with more comprehensive knowledge. We provide source codes and pretrained models to reproduce our results at https://github.com/d223302/albert-embryology.

The success of pretrained contextual encoders, such as ELMo and BERT, has brought a great deal of interest in what these models learn: do they, without explicit supervision, learn to encode meaningful notions of linguistic structure? If so, how is this structure encoded? To investigate this, we introduce latent subclass learning (LSL): a modification to classifier-based probing that induces a latent categorization (or ontology) of the probe’s inputs. Without access to fine-grained gold labels, LSL extracts emergent structure from input representations in an interpretable and quantifiable form. In experiments, we find strong evidence of familiar categories, such as a notion of personhood in ELMo, as well as novel ontological distinctions, such as a preference for fine-grained semantic roles on core arguments. Our results provide unique new evidence of emergent structure in pretrained encoders, including departures from existing annotations which are inaccessible to earlier methods.

There is an increasing interest in developing text-based relational reasoning systems, which are capable of systematically reasoning about the relationships between entities mentioned in a text. However, there remains a substantial performance gap between NLP models for relational reasoning and models based on graph neural networks (GNNs), which have access to an underlying symbolic representation of the text. In this work, we investigate how the structured knowledge of a GNN can be distilled into various NLP models in order to improve their performance. We first pre-train a GNN on a reasoning task using structured inputs and then incorporate its knowledge into an NLP model (e.g., an LSTM) via knowledge distillation. To overcome the difficulty of cross-modal knowledge transfer, we also employ a contrastive learning based module to align the latent representations of NLP models and the GNN. We test our approach with two state-of-the-art NLP models on 13 different inductive reasoning datasets from the CLUTRR benchmark and obtain significant improvements.

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system greatly by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.

Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. Our model, which combines deep learning and graph reasoning, achieves remarkable results in benchmark datasets such as DROP.

We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the complicated reasoning process and solve it with a one-step “black box” model. Inspired by human cognitive processes, in this paper we propose a sequential approach for this task which explicitly models each step of the reasoning process with neural network modules. In particular, five reasoning modules are designed and learned in an end-to-end manner, which leads to a more interpretable model. Experimental results on the ROPES dataset demonstrate the effectiveness and explainability of our proposed approach.

Question-driven summarization has been recently studied as an effective approach to summarizing the source document to produce concise but informative answers for non-factoid questions. In this work, we propose a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question-driven summarization and, meanwhile, provide justifications for the generated summaries. Specifically, we jointly model the relevance to the question and the interrelation among different sentences via a human-like multi-hop inference module, which captures important sentences for justifying the summarized answer. A gated selective pointer generator network with a multi-view coverage mechanism is designed to integrate diverse information from different perspectives. Experimental results show that the proposed method consistently outperforms state-of-the-art methods on two non-factoid QA datasets, namely WikiHow and PubMedQA.

This paper proposes a pre-training based automated Chinese essay scoring method. The method involves three components: weakly supervised pre-training, supervised cross- prompt fine-tuning and supervised target- prompt fine-tuning. An essay scorer is first pre- trained on a large essay dataset covering diverse topics and with coarse ratings, i.e., good and poor, which are used as a kind of weak supervision. The pre-trained essay scorer would be further fine-tuned on previously rated es- says from existing prompts, which have the same score range with the target prompt and provide extra supervision. At last, the scorer is fine-tuned on the target-prompt training data. The evaluation on four prompts shows that this method can improve a state-of-the-art neural essay scorer in terms of effectiveness and domain adaptation ability, while in-depth analysis also reveals its limitations..

The data imbalance problem is a crucial issue for the multi-label text classification. Some existing works tackle it by proposing imbalanced loss objectives instead of the vanilla cross-entropy loss, but their performances remain limited in the cases of extremely imbalanced data. We propose a hybrid solution which adapts general networks for the head categories, and few-shot techniques for the tail categories. We propose a Hybrid-Siamese Convolutional Neural Network (HSCNN) with additional technical attributes, i.e., a multi-task architecture based on Single and Siamese networks; a category-specific similarity in the Siamese structure; a specific sampling method for training HSCNN. The results using two benchmark datasets and three loss objectives show that our method can improve the performance of Single networks with diverse loss objectives on the tail or entire categories.

The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences. Most existing models tackle this problem by stacking CNN and RNN models, which easily leads to feature redundancy and overfitting because of relatively limited datasets. In this paper, we propose a simple yet effective model called Multi-scale Orthogonal inDependEnt LSTM (MODE-LSTM), which not only has effective parameters and good generalization ability, but also considers multiscale n-gram features. We disentangle the hidden state of the LSTM into several independently updated small hidden states and apply an orthogonal constraint on their recurrent matrices. We then equip this structure with sliding windows of different sizes for extracting multi-scale n-gram features. Extensive experiments demonstrate that our model achieves better or competitive performance against state-of-the-art baselines on eight benchmark datasets. We also combine our model with BERT to further boost the generalization performance.

We aim to leverage human and machine intelligence together for attention supervision. Specifically, we show that human annotation cost can be kept reasonably low, while its quality can be enhanced by machine self-supervision. Specifically, for this goal, we explore the advantage of counterfactual reasoning, over associative reasoning typically used in attention supervision. Our empirical results show that this machine-augmented human attention supervision is more effective than existing methods requiring a higher annotation cost, in text classification tasks, including sentiment analysis and news categorization.

Emojis are able to express various linguistic components, including emotions, sentiments, events, etc. Predicting the proper emojis associated with text provides a way to summarize the text accurately, and it has been proven to be a good auxiliary task to many Natural Language Understanding (NLU) tasks. Labels in existing emoji prediction datasets are all passage-based and are usually under the multi-class classification setting. However, in many cases, one single emoji cannot fully cover the theme of a piece of text. It is thus useful to infer the part of text related to each emoji. The lack of multi-label and aspect-level emoji prediction datasets is one of the bottlenecks for this task. This paper annotates an emoji prediction dataset with passage-level multi-class/multi-label, and aspect-level multi-class annotations. We also present a novel annotation method with which we generate the aspect-level annotations. The annotations are generated heuristically, taking advantage of the self-attention mechanism in Transformer networks. We validate the annotations both automatically and manually to ensure their quality. We also benchmark the dataset with a pre-trained BERT model.

Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-Net), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-Net employs a recurrent event encoder to encode past facts, and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RE-Net, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets.

Existing works have proved that using law articles as external knowledge can improve the performance of the Legal Judgment Prediction. However, they do not fully use law article information and most of the current work is only for single label samples. In this paper, we propose a Law Article Element-aware Multi-representation Model (LEMM), which can make full use of law article information and can be used for multi-label samples. The model uses the labeled elements of law articles to extract fact description features from multiple angles. It generates multiple representations of a fact for classification. Every label has a law-aware fact representation to encode more information. To capture the dependencies between law articles, the model also introduces a self-attention mechanism between multiple representations. Compared with baseline models like TopJudge, this model improves the accuracy of 5.84%, the macro F1 of 6.42%, and the micro F1 of 4.28%.