COLING 2020 论文列表

Efficient document summarization requires evaluation measures that can not only rank a set of systems based on an average score, but also highlight which individual summary is better than another. However, despite the very active research on summarization approaches, few works have proposed new evaluation measures in the recent years. The standard measures relied upon for the development of summarization systems are most often ROUGE and BLEU which, despite being efficient in overall system ranking, remain lexical in nature and have a limited potential when it comes to training neural networks. In this paper, we present a new hybrid evaluation measure for summarization, called HOLMS, that combines both language models pre-trained on large corpora and lexical similarity measures. Through several experiments, we show that HOLMS outperforms ROUGE and BLEU substantially in its correlation with human judgments on several extractive summarization datasets for both linguistic quality and pyramid scores.

Question answering over dialogue, a specialized machine reading comprehension task, aims to comprehend a dialogue and to answer specific questions. Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e.g., relationships between speakers). In this paper, we introduce a new approach for the task, featured by its novelty in structuring dialogue and integrating background knowledge for reasoning. Specifically, different from previous “structure-less” approaches, our method organizes a dialogue as a “relational graph”, using edges to represent relationships between entities. To encode this relational graph, we devise a relational graph convolutional network (R-GCN), which can traverse the graph’s topological structure and effectively encode multi-relational knowledge for reasoning. The extensive experiments have justified the effectiveness of our approach over competitive baselines. Moreover, a deeper analysis shows that our model is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences.

Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relational facts. To improve inter-sentence reasoning, we propose to characterize the complex interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA). In GEDA, sentence representation generated by the sentence-to-relation (S2R) attention is refined and synthesized by a Heterogeneous Graph Convolutional Network before being fed into the relation-to-sentence (R2S) attention . We further design a simple yet effective regularizer based on the natural duality of the S2R and R2S attention, whose weights are also supervised by the supporting evidence of relation instances during training. An extensive set of experiments on an existing large-scale dataset show that our model achieve competitive performance, especially for the inter-sentence relation extraction, while the neural predictions can also be interpretable and easily observed.

We propose a contextualised graph convolution network over multiple dependency-based sub-graphs for relation extraction. A novel method to construct multiple sub-graphs using words in shortest dependency path and words linked to entities in the dependency parse is proposed. Graph convolution operation is performed over the resulting multiple sub-graphs to obtain more informative features useful for relation extraction. Our experimental results show that the proposed method achieves superior performance over the existing GCN-based models achieving state-of-the-art performance on cross-sentence n-ary relation extraction dataset and SemEval 2010 Task 8 sentence-level relation extraction dataset. Our model also achieves a comparable performance to the SoTA on the TACRED dataset.

We describe the collection of transcription corrections and grammatical error annotations for the CrowdED Corpus of spoken English monologues on business topics. The corpus recordings were crowdsourced from native speakers of English and learners of English with German as their first language. The new transcriptions and annotations are obtained from different crowdworkers: we analyse the 1108 new crowdworker submissions and propose that they can be used for automatic transcription post-editing and grammatical error correction for speech. To further explore the data we train grammatical error detection models with various configurations including pre-trained and contextual word representations as input, additional features and auxiliary objectives, and extra training data from written error-annotated corpora. We find that a model concatenating pre-trained and contextual word representations as input performs best, and that additional information does not lead to further performance gains.

Pre-trained language models provide the foundations for state-of-the-art performance across a wide range of natural language processing tasks, including text classification. However, most classification datasets assume a large amount labeled data, which is commonly not the case in practical settings. In particular, in this paper we compare the performance of a light-weight linear classifier based on word embeddings, i.e., fastText (Joulin et al., 2017), versus a pre-trained language model, i.e., BERT (Devlin et al., 2019), across a wide range of datasets and classification tasks. In general, results show the importance of domain-specific unlabeled data, both in the form of word embeddings or language models. As for the comparison, BERT outperforms all baselines in standard datasets with large training sets. However, in settings with small training datasets a simple method like fastText coupled with domain-specific word embeddings performs equally well or better than BERT, even when pre-trained on domain-specific data.

Document-level Relation Extraction (RE) is particularly challenging due to complex semantic interactions among multiple entities in a document. Among exiting approaches, Graph Convolutional Networks (GCN) is one of the most effective approaches for document-level RE. However, traditional GCN simply takes word nodes and adjacency matrix to represent graphs, which is difficult to establish direct connections between distant entity pairs. In this paper, we propose Global Context-enhanced Graph Convolutional Networks (GCGCN), a novel model which is composed of entities as nodes and context of entity pairs as edges between nodes to capture rich global context information of entities in a document. Two hierarchical blocks, Context-aware Attention Guided Graph Convolution (CAGGC) for partially connected graphs and Multi-head Attention Guided Graph Convolution (MAGGC) for fully connected graphs, could take progressively more global context into account. Meantime, we leverage a large-scale distantly supervised dataset to pre-train a GCGCN model with curriculum learning, which is then fine-tuned on the human-annotated dataset for further improving document-level RE performance. The experimental results on DocRED show that our model could effectively capture rich global context information in the document, leading to a state-of-the-art result. Our code is available at https://github.com/Huiweizhou/GCGCN.

In this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the input training data, model size, and the presence of Whole Word Masking (WWM) we were able to attain SoTA performance across a set of document classification and named entity recognition (NER) tasks for both models of base and large size. We adopt an evaluation driven approach in training these models and our results indicate that both adding more data and utilizing WWM improve model performance. By benchmarking against existing German models, we show that these models are the best German models to date. All trained models will be made publicly available to the research community.

Standard image caption generation systems produce generic descriptions of images and do not utilize any contextual information or world knowledge. In particular, they are unable to generate captions that contain references to the geographic context of an image, for example, the location where a photograph is taken or relevant geographic objects around an image location. In this paper, we develop a geo-aware image caption generation system, which incorporates geographic contextual information into a standard image captioning pipeline. We propose a way to build an image-specific representation of the geographic context and adapt the caption generation network to produce appropriate geographic names in the image descriptions. We evaluate our system on a novel captioning dataset that contains contextualized captions and geographic metadata and achieve substantial improvements in BLEU, ROUGE, METEOR and CIDEr scores. We also introduce a new metric to assess generated geographic references directly and empirically demonstrate our system’s ability to produce captions with relevant and factually accurate geographic referencing.

Corporate mergers and acquisitions (M&A) account for billions of dollars of investment globally every year and offer an interesting and challenging domain for artificial intelligence. However, in these highly sensitive domains, it is crucial to not only have a highly robust/accurate model, but be able to generate useful explanations to garner a user’s trust in the automated system. Regrettably, the recent research regarding eXplainable AI (XAI) in financial text classification has received little to no attention, and many current methods for generating textual-based explanations result in highly implausible explanations, which damage a user’s trust in the system. To address these issues, this paper proposes a novel methodology for producing plausible counterfactual explanations, whilst exploring the regularization benefits of adversarial training on language models in the domain of FinTech. Exhaustive quantitative experiments demonstrate that not only does this approach improve the model accuracy when compared to the current state-of-the-art and human performance, but it also generates counterfactual explanations which are significantly more plausible based on human trials.

When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction. A novice user might need an object explained piece by piece, while for an expert, talking about the complex object (e.g. a wall or railing) directly may be more succinct and efficient. We show how to generate building instructions at different levels of abstraction in Minecraft. We introduce the use of hierarchical planning to this end, a method from AI planning which can capture the structure of complex objects neatly. A crowdsourcing evaluation shows that the choice of abstraction level matters to users, and that an abstraction strategy which balances low-level and high-level object descriptions compares favorably to ones which don’t.

Math word problem solving is an emerging research topic in Natural Language Processing. Recently, to address the math word problem-solving task, researchers have applied the encoder-decoder architecture, which is mainly used in machine translation tasks. The state-of-the-art neural models use hand-crafted features and are based on generation methods. In this paper, we propose the GEO (Generation of Equations by utilizing Operators) model that does not use hand-crafted features and addresses two issues that are present in existing neural models: 1. missing domain-specific knowledge features and 2. losing encoder-level knowledge. To address missing domain-specific feature issue, we designed two auxiliary tasks: operation group difference prediction and implicit pair prediction. To address losing encoder-level knowledge issue, we added an Operation Feature Feed Forward (OP3F) layer. Experimental results showed that the GEO model outperformed existing state-of-the-art models on two datasets, 85.1% in MAWPS, and 62.5% in DRAW-1K, and reached comparable performance of 82.1% in ALG514 dataset.

In this study, we propose a beam search method to obtain diverse outputs in a local sequence transduction task where most of the tokens in the source and target sentences overlap, such as in grammatical error correction (GEC). In GEC, it is advisable to rewrite only the local sequences that must be rewritten while leaving the correct sequences unchanged. However, existing methods of acquiring various outputs focus on revising all tokens of a sentence. Therefore, existing methods may either generate ungrammatical sentences because they force the entire sentence to be changed or produce non-diversified sentences by weakening the constraints to avoid generating ungrammatical sentences. Considering these issues, we propose a method that does not rewrite all the tokens in a text, but only rewrites those parts that need to be diversely corrected. Our beam search method adjusts the search token in the beam according to the probability that the prediction is copied from the source sentence. The experimental results show that our proposed method generates more diverse corrections than existing methods without losing accuracy in the GEC task.

For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.

Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel versions of existing small supervised datasets, which largely constrain their potential. In this paper, we propose a large-scale, general-domain dataset, GenWiki. Our unsupervised dataset has 1.3M text and graph examples, respectively. With a human-annotated test set, we provide this new benchmark dataset for future research on unsupervised text generation from knowledge graphs.

Parliamentary debates present a valuable language resource for analyzing comprehensive options in electing representatives under a functional, free society. However, the esoteric nature of political speech coupled with non-linguistic aspects such as political cohesion between party members presents a complex and underexplored task of contextual parliamentary debate analysis. We introduce GPolS, a neural model for political speech sentiment analysis jointly exploiting both semantic language representations and relations between debate transcripts, motions, and political party members. Through experiments on real-world English data and by visualizing attention, we provide a use case of GPolS as a tool for political speech analysis and polarity prediction.

Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.

We present experiments on biomedical text simplification in French. We use two kinds of corpora – parallel sentences extracted from existing health comparable corpora in French and WikiLarge corpus translated from English to French – and a lexicon that associates medical terms with paraphrases. Then, we train neural models on these parallel corpora using different ratios of general and specialized sentences. We evaluate the results with BLEU, SARI and Kandel scores. The results point out that little specialized data helps significantly the simplification.

Now that the performance of coreference resolvers on the simpler forms of anaphoric reference has greatly improved, more attention is devoted to more complex aspects of anaphora. One limitation of virtually all coreference resolution models is the focus on single-antecedent anaphors. Plural anaphors with multiple antecedents-so-called split-antecedent anaphors (as in John met Mary. They went to the movies) have not been widely studied, because they are not annotated in ONTONOTES and are relatively infrequent in other corpora. In this paper, we introduce the first model for unrestricted resolution of split-antecedent anaphors. We start with a strong baseline enhanced by BERT embeddings, and show that we can substantially improve its performance by addressing the sparsity issue. To do this, we experiment with auxiliary corpora where split-antecedent anaphors were annotated by the crowd, and with transfer learning models using element-of bridging references and single-antecedent coreference as auxiliary tasks. Evaluation on the gold annotated ARRAU corpus shows that the out best model uses a combination of three auxiliary corpora achieved F1 scores of 70% and 43.6% when evaluated in a lenient and strict setting, respectively, i.e., 11 and 21 percentage points gain when compared with our baseline.