Elamur Research⌕
☰
home / papers / 2023 / Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition

Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition

Summary

Dialogue discourse parsing builds a dependency structure over the utterances of a multi-party conversation, linking them through SDRT-style discourse relations. Annotated data for this task is scarce and costly to produce. Earlier multitask approaches paired parsing with reading comprehension or dropped pronoun recovery, but those tasks need extra human labels. This paper instead pairs parsing with addressee recognition. That task already has large corpora, and its reply-to links partly coincide with discourse links.

The method has two stages:

  • Data selection. An actor-critic reinforcement-learning agent selects the addressee-recognition dialogues that most improve parsing. Its reward is link F1 on the parsing development set.
  • Multitask learning. A task-aware structure transformer scores the importance of each neuron for each task. Neurons useful to both tasks are updated jointly, and the remaining ones are updated only by their own task.

On Molweni and STAC, the system beats state-of-the-art baselines. It does so while discarding most of the auxiliary training data. This shows that parsing can gain from a neighboring task without any new annotation effort.

Key points

  • The model is evaluated on the Molweni and STAC dialogue discourse corpora and outperforms SOTA baselines, including SSP. Code is released as RLTST (github.com/yxfanSuda/RLTST).
  • The backbone has three parts:
    • BERT utterance encoding followed by a BiGRU;
    • a Structure Transformer whose edge features are speaker, turn, and relative distance;
    • MLP classifiers that predict links and relation types.
  • The reinforcement-learning selector removes roughly 80% of the addressee-recognition training examples and still improves parsing.
  • Gains appear mainly on frequent relations such as QAP, Comment, Acknowledgement, Continuation, and Elaboration. Rare relations are still seldom predicted.
  • The authors note two limitations. Relation gains mostly follow from better link prediction. Using the small parsing data in the reverse direction does little to improve addressee recognition.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Discourse analysis

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2023.emnlp-main.526

@inproceedings{fan2023improving,
  title = {{Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition}},
  author = {Fan, Yaxin and Jiang, Feng and Li, Peifeng and Kong, Fang and Zhu, Qiaoming},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  doi = {10.18653/v1/2023.emnlp-main.526},
  url = {https://doi.org/10.18653/v1/2023.emnlp-main.526}
}

References

28 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Nicholas Asher, Julie Hunter, Mathieu Morey, Farah Benamara, and Stergos Afantenos. 2016. Discourse Structure and Dialogue Acts in Multiparty Dialogue: the STAC Corpus. In Proceedings of the 10th International Conference on Language Resources and Evaluation, pages 2721–2727. find our card
  2. Nicholas Asher and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press. find
  3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pages 4171–4186. find
  4. Asia Conference on Language, Information and Computation, pages 598–608. find
  5. Wenpeng Hu, Zhangming Chan, Bing Liu, Dongyan Zhao, Jinwen Ma, and Rui Yan. 2019. GSN: A Graph-Structured Network for Multi-Party Dialogues. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, pages 5010–5016. find
  6. Vijay Konda and John Tsitsiklis. 1999. Actor-Critic Algorithms. In Proceedings of the Advances in Neural Information Processing Systems, pages 1008–1014. find
  7. Ran Le, Wenpeng Hu, Mingyue Shang, Zhenjun You, Lidong Bing, Dongyan Zhao, and Rui Yan. 2019. Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Internat… find
  8. Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, and Bing Qin. 2020. Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure. In Proceedings of the 28th International Conference on Computational Linguistics, page… find
  9. Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, and Erich Elsen. 2020. Rigging the Lottery: Making All Tickets Winners. In Proceedings of the 37th International Conference on Machine Learning, pages 2943–2952. find
  10. Shangqing Liu, Yu Chen, Xiaofei Xie, Jing Kai Siow, and Yang Liu. 2020. Retrieval-Augmented Generation for Code Summarization via Hybrid GNN. In Proceedings of the International Conference on Learning Representations, pages 1–16. find
  11. Yaxin Fan and Feng Jiang. 2023. Uncovering the potential of chatgpt for discourse analysis in dialogue: An empirical study. arXiv preprint arXiv:2305.08391. find
  12. Zhengyuan Liu and Nancy Chen. 2021. Improving Multi-Party Dialogue Discourse Parsing via Domain Integration. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 122–127. find our card
  13. Yaxin Fan, Peifeng Li, Fang Kong, and Qiaoming Zhu. 2022. A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 912–921. find our card
  14. Xiachong Feng, Xiaocheng Feng, Bing Qin, and Xinwei Geng. 2021. Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, pages 3808–3814. find
  15. Jia-Chen Gu, Chongyang Tao, Zhenhua Ling, Can Xu, Xiubo Geng, and Daxin Jiang. 2021. MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conferen… find
  16. Yuchen He, Zhuosheng Zhang, and Hai Zhao. 2021. Multi-tasking Dialogue Comprehension with Discourse Parsing. In Proceedings of the 35th Pacific William C Mann and Sandra A Thompson. 1988. Rhetorical Structure Theory: Toward a functional theory of text organization. Text-interdisciplinary Journal for… find our card
  17. Hiroki Ouchi and Yuta Tsuboi. 2016. Addressee and Response Selection for Multi-Party Conversation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2133–2143. find
  18. Rajkumar Pujari, Erik Oveson, Priyanka Kulkarni, and Elnaz Nouri. 2022. Reinforcement guided multi-task learning framework for low-resource stereotype detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6703–6712. find
  19. Zhouxing Shi and Minlie Huang. 2019. A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 7007–7014. find
  20. Yang Sun, Nan Yu, and Guohong Fu. 2021. A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2949–2958. find
  21. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of the Advances in Neural Information Processing Systems, pages 5998–6008. find
  22. 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 30th International Joint Conference on Artificial Intelligence, pages 3943–3949. find
  23. Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, and Ji-Rong Wen. 2021. A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsiin Chinese Conversational Speech. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics an… find
  24. Zhiquan Ye, Yuxia Geng, Jiaoyan Chen, Jingmin Chen, Xiaoxiao Xu, SuHang Zheng, Feng Wang, Jun Zhang, and Huajun Chen. 2020. Zero-shot text classification via reinforced self-training. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3014–3024. find
  25. Nan Yu, Guohong Fu, and Min Zhang. 2022. Speaker-Aware Discourse Parsing on Multi-Party Dialogues. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5372–5382. find our card
  26. Rui Zhang, Honglak Lee, Lazaros Polymenakos, and Dragomir Radev. 2018. Addressee and Response Selection in Multi-Party Conversations With Speaker Interaction RNNs. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 5690–5697. find
  27. Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, and Guodong Zhou. 2019. Modeling Graph Structure in Transformer for Better AMR-to-Text Generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural… find
  28. Michael Zhu and Suyog Gupta. 2018. To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression. In Proceedings of the International Conference on Learning Representations, pages 1–10. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/fan-2023-improving-dialogue-discourse-parsing-reply/