A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

Wang, Ante; Song, Linfeng; Jiang, Hui; Lai, Shaopeng; Yao, Junfeng; Zhang, Min; Su, Jinsong

doi:10.24963/ijcai.2021/543

A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

Ante Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, Jinsong Su

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3943-3949.

https://doi.org/10.24963/ijcai.2021/543

Keywords

Natural Language Processing: Tagging, Chunking, and Parsing
Natural Language Processing: Discourse
Natural Language Processing: Dialogue

Abstract

Conversational discourse structures aim to describe how a dialogue is organized, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e.g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

Ante Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, and Jinsong Su. 2021. A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3943–3949. https://doi.org/10.24963/ijcai.2021/543

@inproceedings{ijcai2021p543,
  title     = {A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues},
  author    = {Wang, Ante and Song, Linfeng and Jiang, Hui and Lai, Shaopeng and Yao, Junfeng and Zhang, Min and Su, Jinsong},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {3943--3949},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/543},
  url       = {https://doi.org/10.24963/ijcai.2021/543},
}

TY  - CPAPER
TI  - A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues
AU  - Wang, Ante
AU  - Song, Linfeng
AU  - Jiang, Hui
AU  - Lai, Shaopeng
AU  - Yao, Junfeng
AU  - Zhang, Min
AU  - Su, Jinsong
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3943
EP  - 3949
DO  - 10.24963/ijcai.2021/543
UR  - https://doi.org/10.24963/ijcai.2021/543
ER  -