Articles

Fake news with textual and visual contents has a better story-telling ability than text-only con- tents, and can be spread quickly with social media. People can be easily deceived by such fake news, and traditional expert identification is labor-intensive. Therefore, automatic detec- tion of multimodal fake news has become a …...

Open Knowledge Graphs (OpenKG) refer to a set of (head noun phrase, relation phrase, tail noun phrase) triples such as (tesla, return to, new york) extracted from a corpus using Ope- nIE tools. While OpenKGs are easy to boot- strap for a domain, they are very sparse and far from …...

In end-to-end speech translation, acoustic rep- resentations learned by the encoder are usually fixed and static, from the perspective of the de- coder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in speech translation. In this paper, we show the benefits of varying acoustic states according …...

To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained genera- tion model is trained to learn response gener- ation under the simplified framework of one- to-one mapping. …...

Existing pre-trained models for knowledge- graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure dur- ing encoding and lack elaborate pre-training tasks to explicitly model graph-text align- ments. To tackle these problems, we propose a graph-text joint …...

Relation extraction is an important task in in- formation extraction and retrieval that aims to extract relations among the given entities from running texts. To achieve a good performance for this task, previous studies have shown that a good modeling of the contextual informa- tion is required, where the dependency …...

The lack of reliable automatic evaluation met- rics is a major impediment to the development of open-domain dialogue systems. Various reference-based metrics have been proposed to calculate a score between a predicted re- sponse and a small set of references. How- ever, these metrics show unsatisfactory correla- tions with human …...

Since traditional tokenizers are isolated from a downstream task and model, they cannot out- put an appropriate tokenization depending on the task and model, although recent studies im- ply that the appropriate tokenization improves the performance. In this paper, we propose a novel method to find an appropriate tokeniza- tion …...

End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real- time, is useful in many scenarios but has not been fully investigated. In this work, we pro- pose RealTranS, an end-to-end model for SST. To bridge the modality gap between speech …...

Evidence-based fact checking aims to verify the truthfulness of a claim against evidence ex- tracted from textual sources. Learning a rep- resentation that effectively captures relations between a claim and evidence can be challeng- ing. Recent state-of-the-art approaches have developed increasingly sophisticated models based on graph structures. We present a …...

Chinese spelling check (CSC) is a task to detect and correct spelling errors in Chinese text. Most state-of-the-art works on the CSC task adopt a BERT-based non-autoregressive language model, which relies on the output independence assumption. The inappropri- ate independence assumption prevents BERT- based models from learning the dependencies among …...

Current storytelling systems focus more on generating stories with coherent plots regard- less of the narration style, which is impor- tant for controllable text generation. There- fore, we propose a new task, stylized story gen- eration, namely generating stories with speci- fied style given a leading context. To tackle the …...

Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types. In real-world applications, ED typically does not have suf- ficient labelled data, thus can be formulated as a few-shot learning problem. To tackle the issue of low sample diversity in few-shot ED, …...

Medical entity retrieval is an integral compo- nent for understanding and communicating in- formation across various health systems. Cur- rent approaches tend to work well on specific medical domains but generalize poorly to un- seen sub-specialties. This is of increasing con- cern under a public health crisis as new med- …...

Understanding historical events is necessary for the study of contemporary society, cul- ture, and politics. In this work, we focus on the event extraction task (EE) to detect event trigger words and their arguments in a novel domain of historical texts. In particular, we introduce a new EE dataset for …...

Open Information Extraction (OpenIE) aims to extract structured relational tuples (subject, relation, object) from sentences, and plays a critical role in many NLP applications. Ex- isting solutions perform extraction at sentence level, without referring to any additional con- textual information. In reality, however, a sen- tence typically exists as part …...

Domain Adaptation is a fundamental prob- lem in machine learning and natural language processing. In this paper, we study the do- main adaptation problem from the perspective of instance weighting. Conventional instance weighting approaches cannot learn the weights which make the model generalize well in target domain. To tackle this …...

Stance detection determines whether the au- thor of a text is in favor of, against or neu- tral to a specific target and provides valuable insights into important events such as presi- dential election. However, progress on stance detection has been hampered by the absence of large annotated datasets. In …...

Previous work on adversarial attacks on depen- dency parsers has mostly focused on attack methods, as opposed to the quality of adver- sarial examples, which in previous work has been relatively low. To address this gap, we propose a method to generate high-quality ad- versarial examples with a higher number …...

Incorporating attribute information such as user and product features into deep neural net- works has been shown to be useful in senti- ment analysis. Previous works typically ac- complished this in two ways: concatenating multiple attributes to word/text representation or treating them as a bias to adjust attention dis- tribution. …...