In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant information when utilizing previous dialogue states. Moreover, the relations between the updates of different slots provide vital clues for DST. However, the existing approaches rely only on predefined graphs to indirectly capture the relations. In this paper, we propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states and migrate the gap of utilization between training and testing. Thus, it can dynamically exploit previous dialogue states and avoid introducing error propagation simultaneously. Further, we propose an inter-slot contrastive learning loss to effectively capture the slot co-update relations from dialogue context. Experiments are conducted on the widely used MultiWOZ 2.0 and MultiWOZ 2.1 datasets. The experimental results show that our proposed model achieves the state-of-the-art performance for DST.

Fact verification is a challenging task that requires the retrieval of multiple pieces of evidence from a reliable corpus for verifying the truthfulness of a claim. Although the current methods have achieved satisfactory performance, they still suffer from one or more of the following three problems: (1) unable to extract sufficient contextual information from the evidence sentences; (2) containing redundant evidence information and (3) incapable of capturing the interaction between claim and evidence. To tackle the problems, we propose an evidence fusion network called EvidenceNet. The proposed EvidenceNet model captures global contextual information from various levels of evidence information for deep understanding. Moreover, a gating mechanism is designed to filter out redundant information in evidence. In addition, a symmetrical interaction attention mechanism is also proposed for identifying the interaction between claim and evidence. We conduct extensive experiments based on the FEVER dataset. The experimental results have shown that the proposed EvidenceNet model outperforms the current fact verification methods and achieves the state-of-the-art performance.

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Named Entity Recognition (NER) is a fundamental problem in Natural Language Processing and has received much research attention. Although the current neural-based NER approaches have achieved the state-of-the-art performance, they still suffer from one or more of the following three problems in their architectures: (1) boundary tag sparsity, (2) lacking of global decoding information; and (3) boundary error propagation. In this paper, we propose a novel Boundary-aware Bidirectional Neural Networks (Ba-BNN) model to tackle these problems for neural-based NER. The proposed Ba-BNN model is constructed based on the structure of pointer networks for tackling the first problem on boundary tag sparsity. Moreover, we also use a boundary-aware binary classifier to capture the global decoding information as input to the decoders. In the Ba-BNN model, we propose to use two decoders to process the information in two different directions (i.e., from left-to-right and right-to-left). The final hidden states of the left-to-right decoder are obtained by incorporating the hidden states of the right-to-left decoder in the decoding process. In addition, a boundary retraining strategy is also proposed to help reduce boundary error propagation caused by the pointer networks in boundary detection and entity classification. We have conducted extensive experiments based on three NER benchmark datasets. The performance results have shown that the proposed Ba-BNN model has outperformed the current state-of-the-art models.