COLING 2020 Papers

Natural Language Sentence Matching (NLSM) serves as the core of many natural language processing tasks. 1) Most previous work develops a single specific neural model for NLSM tasks. 2) There is no previous work considering adversarial attack to improve the performance of NLSM tasks. 3) Adversarial attack is usually used to generate adversarial samples that can fool neural models. In this paper, we first find a phenomenon that different categories of samples have different vulnerabilities. Vulnerability is the difficulty degree in changing the label of a sample. Considering the phenomenon, we propose a general two-stage training framework to enhance neural models with Vulnerability via Adversarial Attack (VAA). We design criteria to measure the vulnerability which is obtained by adversarial attack. VAA framework can be adapted to various neural models by incorporating the vulnerability. In addition, we prove a theorem and four corollaries to explain the factors influencing vulnerability effectiveness. Experimental results show that VAA significantly improves the performance of neural models on NLSM datasets. The results are also consistent with the theorem and corollaries. The code is released on https://github.com/rzhangpku/VAA.

Text summarization aims to compress a textual document to a short summary while keeping salient information. Extractive approaches are widely used in text summarization because of their fluency and efficiency. However, most of existing extractive models hardly capture inter-sentence relationships, particularly in long documents. They also often ignore the effect of topical information on capturing important contents. To address these issues, this paper proposes a graph neural network (GNN)-based extractive summarization model, enabling to capture inter-sentence relationships efficiently via graph-structured document representation. Moreover, our model integrates a joint neural topic model (NTM) to discover latent topics, which can provide document-level features for sentence selection. The experimental results demonstrate that our model not only substantially achieves state-of-the-art results on CNN/DM and NYT datasets but also considerably outperforms existing approaches on scientific paper datasets consisting of much longer documents, indicating its better robustness in document genres and lengths. Further discussions show that topical information can help the model preselect salient contents from an entire document, which interprets its effectiveness in long document summarization.

Domain knowledge is important for building Natural Language Processing (NLP) systems for low-resource settings, such as in the clinical domain. In this paper, a novel joint training method is introduced for adding knowledge base information from the Unified Medical Language System (UMLS) into language model pre-training for some clinical domain corpus. We show that in three different downstream clinical NLP tasks, our pre-trained language model outperforms the corresponding model with no knowledge base information and other state-of-the-art models. Specifically, in a natural language inference task applied to clinical texts, our knowledge base pre-training approach improves accuracy by up to 1.7%, whereas in clinical name entity recognition tasks, the F1-score improves by up to 1.0%. The pre-trained models are available at https://github.com/noc-lab/clinical-kb-bert.

Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages. Considering that most emotions usually have few causes mentioned in their contexts, we present a novel end-to-end Pair Graph Convolutional Network (PairGCN) to model pair-level contexts so that to capture the dependency information among local neighborhood candidate pairs. Moreover, in the graphical network, contexts are grouped into three types and each type of contexts is propagated by its own way. Experiments on a benchmark Chinese emotion-cause pair extraction corpus demonstrate the effectiveness of the proposed model.

In this paper, we present Chinese lexical fusion recognition, a new task which could be regarded as one kind of coreference recognition. First, we introduce the task in detail, showing the relationship with coreference recognition and differences from the existing tasks. Second, we propose an end-to-end model for the task, handling mentions as well as coreference relationship jointly. The model exploits the state-of-the-art contextualized BERT representations as an encoder, and is further enhanced with the sememe knowledge from HowNet by graph attention networks. We manually annotate a benchmark dataset for the task and then conduct experiments on it. Results demonstrate that our final model is effective and competitive for the task. Detailed analysis is offered for comprehensively understanding the new task and our proposed model.

Semantic models derived from visual information have helped to overcome some of the limitations of solely text-based distributional semantic models. Researchers have demonstrated that text and image-based representations encode complementary semantic information, which when combined provide a more complete representation of word meaning, in particular when compared with data on human conceptual knowledge. In this work, we reveal that these vision-based representations, whilst quite effective, do not make use of all the semantic information available in the neural network that could be used to inform vector-based models of semantic representation. Instead, we build image-based meta-embeddings from computer vision models, which can incorporate information from all layers of the network, and show that they encode a richer set of semantic attributes and yield a more complete representation of human conceptual knowledge.

We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.

A humanized dialogue system is expected to generate empathetic replies, which should be sensitive to the users’ expressed emotion. The task of empathetic dialogue generation is proposed to address this problem. The essential challenges lie in accurately capturing the nuances of human emotion and considering the potential of user feedback, which are overlooked by the majority of existing work. In response to this problem, we propose a multi-resolution adversarial model – EmpDG, to generate more empathetic responses. EmpDG exploits both the coarse-grained dialogue-level and fine-grained token-level emotions, the latter of which helps to better capture the nuances of user emotion. In addition, we introduce an interactive adversarial learning framework which exploits the user feedback, to identify whether the generated responses evoke emotion perceptivity in dialogues. Experimental results show that the proposed approach significantly outperforms the state-of-the-art baselines in both content quality and emotion perceptivity.

Emotion lexicons have been shown effective for emotion classification (Baziotis et al., 2018). Previous studies handle emotion lexicon construction and emotion classification separately. In this paper, we propose an emotional network (EmNet) to jointly learn sentence emotions and construct emotion lexicons which are dynamically adapted to a given context. The dynamic emotion lexicons are useful for handling words with multiple emotions based on different context, which can effectively improve the classification accuracy. We validate the approach on two representative architectures – LSTM and BERT, demonstrating its superiority on identifying emotions in Tweets. Our model outperforms several approaches proposed in previous studies and achieves new state-of-the-art on the benchmark Twitter dataset.

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world’s languages lack such resources. Hence, we investigate a more radical form of unsupervised knowledge transfer in the absence of linguistic data. In particular, for the first time we pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images—as a crude approximation of real-world environments—inductively biases the model towards learning natural languages. On the one hand, we show that this substantially benefits machine translation in few-shot settings. On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For instance, in this work we measure the influence of communication success and maximum sequence length on downstream performances. Finally, we introduce a customised adapter layer and annealing strategies for the regulariser of maximum-a-posteriori inference during fine-tuning. These turn out to be crucial to facilitate knowledge transfer and prevent catastrophic forgetting. Compared to a recurrent baseline, our method yields gains of 59.0% 147.6% in BLEU score with only 500 NMT training instances and 65.1% 196.7% with 1,000 NMT training instances across four language pairs. These proof-of-concept results reveal the potential of emergent communication pretraining for both natural language processing tasks in resource-poor settings and extrinsic evaluation of artificial languages.

A common step in developing an understanding of a vertical domain, e.g. shopping, dining, movies, medicine, etc., is curating a taxonomy of categories specific to the domain. These human created artifacts have been the subject of research in embeddings that attempt to encode aspects of the partial ordering property of taxonomies. We compare Box Embeddings, a natural containment representation of category taxonomies, to partial-order embeddings and a baseline Bayes Net, in the context of representing the Medical Subject Headings (MeSH) taxonomy given a set of 300K PubMed articles with subject labels from MeSH. We deeply explore the experimental properties of training box embeddings, including preparation of the training data, sampling ratios and class balance, initialization strategies, and propose a fix to the original box objective. We then present first results in using these techniques for representing a bipartite learning problem (i.e. collaborative filtering) in the presence of taxonomic relations within each partition, inferring disease (anatomical) locations from their use as subject labels in journal articles. Our box model substantially outperforms all baselines for taxonomic reconstruction and bipartite relationship experiments. This performance improvement is observed both in overall accuracy and the weighted spread by true taxonomic depth.

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily available for many IR tasks, for example, patent classes in prior-art retrieval, topical information in Wikipedia articles, or product categories in e-commerce data. We present a framework that learns embeddings for meta-textual categories, and optimizes a pairwise ranking objective for improved matching based on combined embeddings of textual and meta-textual information. We show considerable gains in an experimental evaluation on cross-lingual retrieval in the Wikipedia domain for three language pairs, and in the Patent domain for one language pair. Our results emphasize that the mode of combining different types of information is crucial for model improvement.

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embedding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real-world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks.

In this paper, we deal with two problems in Japanese-English machine translation of news articles. The first problem is the quality of parallel corpora. Neural machine translation (NMT) systems suffer degraded performance when trained with noisy data. Because there is no clean Japanese-English parallel data for news articles, we build a novel parallel news corpus consisting of Japanese news articles translated into English in a content-equivalent manner. This is the first content-equivalent Japanese-English news corpus translated specifically for training NMT systems. The second problem involves the domain-adaptation technique. NMT systems suffer degraded performance when trained with mixed data having different features, such as noisy data and clean data. Though the existing methods try to overcome this problem by using tags for distinguishing the differences between corpora, it is not sufficient. We thus extend a domain-adaptation method using multi-tags to train an NMT model effectively with the clean corpus and existing parallel news corpora with some types of noise. Experimental results show that our corpus increases the translation quality, and that our domain-adaptation method is more effective for learning with the multiple types of corpora than existing domain-adaptation methods are.

Few-shot learning addresses the the problem of learning based on a small amount of training data. Although more well-studied in the domain of computer vision, recent work has adapted the Amazon Review Sentiment Classification (ARSC) text dataset for use in the few-shot setting. In this work, we use the ARSC dataset to study a simple application of transfer learning approaches to few-shot classification. We train a single binary classifier to learn all few-shot classes jointly by prefixing class identifiers to the input text. Given the text and class, the model then makes a binary prediction for that text/class pair. Our results show that this simple approach can outperform most published results on this dataset. Surprisingly, we also show that including domain information as part of the task definition only leads to a modest improvement in model accuracy, and zero-shot classification, without further fine-tuning on few-shot domains, performs equivalently to few-shot classification. These results suggest that the classes in the ARSC few-shot task, which are defined by the intersection of domain and rating, are actually very similar to each other, and that a more suitable dataset is needed for the study of few-shot text classification.

The dissemination of fake news significantly affects personal reputation and public trust. Recently, fake news detection has attracted tremendous attention, and previous studies mainly focused on finding clues from news content or diffusion path. However, the required features of previous models are often unavailable or insufficient in early detection scenarios, resulting in poor performance. Thus, early fake news detection remains a tough challenge. Intuitively, the news from trusted and authoritative sources or shared by many users with a good reputation is more reliable than other news. Using the credibility of publishers and users as prior weakly supervised information, we can quickly locate fake news in massive news and detect them in the early stages of dissemination. In this paper, we propose a novel structure-aware multi-head attention network (SMAN), which combines the news content, publishing, and reposting relations of publishers and users, to jointly optimize the fake news detection and credibility prediction tasks. In this way, we can explicitly exploit the credibility of publishers and users for early fake news detection. We conducted experiments on three real-world datasets, and the results show that SMAN can detect fake news in 4 hours with an accuracy of over 91%, which is much faster than the state-of-the-art models.

Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences. However, most of the existing models suffer from the off-topic problem, namely, the models are prone to generate some unrelated clauses that are somehow involved with certain input terms regardless of the given input data. This problem seriously degrades the quality of the generation results. In this paper, we propose a novel dynamic topic tracker for solving this problem. Different from existing models, our proposed model learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. The recognized topic is used as additional information to guide the generation process and thus alleviates the off-topic problem. The experimental results show that our proposed model can enhance the performance of sentence generation and the off-topic problem is significantly mitigated.

Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for one task (ASR or ST). Our major contribution lies in how these decoders interact with each other: one decoder can attend to different information sources from the other via a dual-attention mechanism. We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual-decoder Transformers, respectively. Extensive experiments on the MuST-C dataset show that our models outperform the previously-reported highest translation performance in the multilingual settings, and outperform as well bilingual one-to-one results. Furthermore, our parallel models demonstrate no trade-off between ASR and ST compared to the vanilla multi-task architecture. Our code and pre-trained models are available at https://github.com/formiel/speech-translation.