Jie Xu


2020

pdf bib
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
Junfan Chen | Richong Zhang | Yongyi Mao | Jie Xu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies. Specifically, we integrate an interactive encoder to jointly model the in-turn dependencies and cross-turn dependencies. The slot-level context is introduced to extract more expressive features for different slots. And a distributed copy mechanism is utilized to selectively copy words from historical system utterances or historical user utterances. Empirical studies demonstrated the superiority of the proposed PIN model.

pdf bib
Neural Dialogue State Tracking with Temporally Expressive Networks
Junfan Chen | Richong Zhang | Yongyi Mao | Jie Xu
Findings of the Association for Computational Linguistics: EMNLP 2020

Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue. In this work, we propose Temporally Expressive Networks (TEN) to jointly model the two types of temporal dependencies in DST. The TEN model utilizes the power of recurrent networks and probabilistic graphical models. Evaluating on standard datasets, TEN is demonstrated to improve the accuracy of turn-level-state prediction and the state aggregation.

2019

pdf bib
Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework
Junfan Chen | Richong Zhang | Yongyi Mao | Hongyu Guo | Jie Xu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean. Such unrealistic assumption is contradictory with the fact that the given labels are often noisy as well, thus leading to significant performance degradation of those models on real-world data. To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. We empirically demonstrate that our approach significantly improves the current art in uncovering the ground-truth relation labels.

2015

pdf bib
Chinese CogBank: Where to See the Cognitive Features of Chinese Words
Bin Li | Xiaopeng Bai | Siqi Yin | Jie Xu
Proceedings of the Third Workshop on Metaphor in NLP

2003

pdf bib
Focus-Marking in Chinese and Malay : A Comparative Perspective
Jie Xu
Proceedings of the 17th Pacific Asia Conference on Language, Information and Computation

1998

pdf bib
Proceedings of the 12th Pacific Asia Conference on Language, Information and Computation
Jin Guo | Kim Teng Lua | Jie Xu
Proceedings of the 12th Pacific Asia Conference on Language, Information and Computation

pdf bib
Grammatical Devices in the Processing of [+Wh] and [+Focus]
Jie Xu
Proceedings of the 12th Pacific Asia Conference on Language, Information and Computation