Elamur Research⌕
☰
home / papers / 2021 / Multi-tasking Dialogue Comprehension with Discourse Parsing

Multi-tasking Dialogue Comprehension with Discourse Parsing

Summary

Reading comprehension over multi-party chat logs is difficult. Turns from several speakers interleave, so related utterances can be far apart while neighbouring ones may have nothing to do with each other. The authors argue that extractive question answering (QA) and dialogue discourse parsing (DP) can inform each other. They present what they call the first model that learns both jointly in a multi-task setup.

A shared pre-trained encoder (BERT-family models) reads the question placed before the dialogue. The QA head predicts answer start and end positions and can label a question unanswerable. The DP head represents each utterance by its separator vector. It combines vector pairs to predict which turn a given utterance attaches to and the type of that relation.

On the Molweni benchmark, joint training improved both QA and DP over single-task baselines, and the authors report state-of-the-art results. The benefit appears mostly on longer dialogues. This suggests explicit discourse structure helps models link distant turns, which matters for chat-based assistants and knowledge extraction.

Key points

  • Data and setup:
    • Experiments use Molweni (Li et al., 2020), a multi-party dialogue MRC dataset with human annotations for both answer spans and discourse relations.
    • Unanswerable questions are included. They are handled by comparing the best span score against a no-answer score.
  • DP features:
    • The pair feature for utterances i and j combines both [SEP] embeddings, their difference and their element-wise product.
    • DP is split into two parts: link prediction (an SVD step over each utterance's pair features) and relation-type classification.
    • Utterances with no parent are attached to a root, forming a dependency tree.
  • Dialogue length: Test dialogues were grouped by number of utterances (≤7, 8–9, ≥10). The QA-only model degraded noticeably on long dialogues. The multi-task model stayed nearly as accurate as on short ones.
  • Case study (BERT wwm):
    • The joint model answered 99 questions correctly that the QA-only model got wrong.
    • Manual inspection credited discourse information in 58 of these 99 cases.
    • QAP (question–answer pair) links contributed most. Clarification Question links contributed little.
  • Error analysis:
    • Multi-tasking handled "who" questions better.
    • "How" questions remained the hardest for both models.
  • Missing figures: The exact EM/F1 and DP scores appear in a section omitted from the extracted text, so this summary gives no specific numbers.

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

Cited by

11 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. arXiv 2110.03269

@inproceedings{he2021multi,
  title = {{Multi-tasking Dialogue Comprehension with Discourse Parsing}},
  author = {He, Yuchen and Zhang, Zhuosheng and Zhao, Hai},
  booktitle = {Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation},
  year = {2021},
  eprint = {2110.03269},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.03269}
}

References

42 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Stergos Afantenos, Eric Kow, Nicholas Asher, and Jérémy Perret. 2015. Discourse parsing for multi-party chat dialogues. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 928–937, Lisbon, Portugal. Association for Computational Linguistics. find our card
  2. James F Allen, Lenhart K Schubert, George M Ferguson, Peter A Heeman, and Chung Hee Hwang. 1994. The trains project: A case study in building a conversational planning agent. Technical report, ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE. find
  3. Nicholas Asher, Julie Hunter, Mathieu Morey, Benamara Farah, and Stergos Afantenos. 2016. Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2721–2727, Portorož, Slo… find our card
  4. Hongxiao Bai and Hai Zhao. 2018. Deep enhanced representation for implicit discourse relation recognition. In Proceedings of the 27th International Conference on Computational Linguistics, pages 571–583, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find our card
  5. Chloé Braud, Maximin Coavoux, and Anders Søgaard. 2017. Cross-lingual RST discourse parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 292–304, Valencia, Spain. Association for Computational Linguistic… find our card
  6. Deng Cai and Hai Zhao. 2017. Pair-aware neural sentence modeling for implicit discourse relation classification. In International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pages 458–466. find
  7. Springer. Erik Cambria, Björn Schuller, Yunqing Xia, and Catherine Havasi. 2013. New avenues in opinion mining and sentiment analysis. IEEE Intelligent systems, 28(2):15– 21. find
  8. Joyce Y. Chai and Rong Jin. 2004. Discourse structure for context question answering. In Proceedings of the Workshop on Pragmatics of Question Answering at HLT-NAACL 2004, pages 23–30, Boston, Massachusetts, USA. Association for Computational Linguistics. find
  9. Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, and Luke Zettlemoyer. 2018. QuAC: Question answering in context. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2174–2184, Brussels, Belgium. Association for Computa… find our card
  10. Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: pre-training text encoders as discriminators rather than generators. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. find
  11. OpenReview.net. 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: Human Langua… find
  12. Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C.H. Hoi, Caiming Xiong, Irwin King, and Michael Lyu. 2020. Discern: Discourse-aware entailment reasoning network for conversational machine reading. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing… find
  13. Karl Moritz Hermann, Tomás Kociský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. Teaching machines to read and comprehend. In Corinna Cortes, Neil D. Lawrence, Daniel D. Lee, Masashi Sugiyama, and Roman Garnett, editors, Advances in Neural Information Proc… find our card
  14. Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston. 2016. The goldilocks principle: Reading children’s books with explicit memory representations. In Yoshua Bengio and Yann LeCun, editors, 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 20… find our card
  15. Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, and Haifeng Tang. 2020. Multi-turn response selection using dialogue dependency relations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1911–1920, Online. Association for Computational Linguistics. find
  16. Shafiq Joty, Giuseppe Carenini, and Raymond T. Ng. 2015. CODRA: A novel discriminative framework for rhetorical analysis. Computational Linguistics, 41(3):385–435. find our card
  17. Guokun Lai, Qizhe Xie, Hanxiao Liu, Yiming Yang, and Eduard Hovy. 2017. RACE: Large-scale ReAding comprehension dataset from examinations. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 785–794, Copenhagen, Denmark. Association for Computational Ling… find our card
  18. Qi Li, Tianshi Li, and Baobao Chang. 2016. Discourse parsing with attention-based hierarchical neural networks. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 362–371, Austin, Texas. Association for Computational Linguistics. find our card
  19. 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
  20. Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, and Ting Liu. 2021. Dadgraph: A discourse-aware dialogue graph neural network for multiparty dialogue machine reading comprehension. CoRR, abs/2104.12377. — [arXiv:2104.12377](https://arxiv.org/abs/2104.12377) find
  21. Yang Liu and Mirella Lapata. 2017. Learning contextually informed representations for linear-time discourse parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1289–1298, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  22. William C Mann and Sandra A Thompson. 1988. Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243–281. find our card
  23. Todor Mihaylov and Anette Frank. 2019. Discourse-aware semantic self-attention for narrative reading comprehension. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), page… find
  24. Eleni Miltsakaki, Rashmi Prasad, Aravind Joshi, and Bonnie Webber. 2004. The Penn Discourse Treebank. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA). find our card
  25. Bita Nejat, Giuseppe Carenini, and Raymond Ng. 2017. Exploring joint neural model for sentence level discourse parsing and sentiment analysis. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 289–298, Saarbrücken, Germany. Association for Computational Linguistics. find our card
  26. Siru Ouyang, Zhuosheng Zhang, and Hai Zhao. 2021. Dialogue graph modeling for conversational machine reading. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3158–3169, Online. Association for Computational Linguistics. find
  27. Julien Perez and Fei Liu. 2017. Dialog state tracking, a machine reading approach using memory network. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 305–314, Valencia, Spain. Association for Computational… find
  28. Lianhui Qin, Zhisong Zhang, Hai Zhao, Zhiting Hu, and Eric Xing. 2017. Adversarial connective-exploiting networks for implicit discourse relation classification. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1006–1017, Vanco… find our card
  29. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics. find our card
  30. Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don’t know: Unanswerable questions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 784–789, Melbourne, Australia. Association for Computational Ling… find our card
  31. Siva Reddy, Danqi Chen, and Christopher D. Manning. 2019. CoQA: A conversational question answering challenge. Transactions of the Association for Computational Linguistics, 7:249–266. find our card
  32. Min Joon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. find our card
  33. OpenReview.net. Zhouxing Shi and Minlie Huang. 2019. A deep sequential model for discourse parsing on multi-party dialogues. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth… find
  34. AAAI Press. Kai Sun, Dian Yu, Jianshu Chen, Dong Yu, Yejin Choi, and Claire Cardie. 2019. DREAM: A challenge data set and models for dialogue-based reading comprehension. Transactions of the Association for Computational Linguistics, 7:217–231. find our card
  35. Ryuichi Takanobu, Minlie Huang, Zhongzhou Zhao, Feng-Lin Li, Haiqing Chen, Xiaoyan Zhu, and Liqiang Nie. 2018. A weakly supervised method for topic segmentation and labeling in goal-oriented dialogues via reinforcement learning. In Jérôme Lang, editor, Proceedings of the Twenty-Seventh International… find
  36. Suzan Verberne, Lou Boves, Nelleke Oostdijk, and Peter-Arno Coppen. 2007. Evaluating discourse-based answer extraction for why-question answering. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 735–736. find
  37. Yizhong Wang, Sujian Li, and Houfeng Wang. 2017. A two-stage parsing method for text-level discourse analysis. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 184–188, Vancouver, Canada. Association for Computational Linguist… find our card
  38. An Yang and Sujian Li. 2018. SciDTB: Discourse dependency TreeBank for scientific abstracts. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 444–449, Melbourne, Australia. Association for Computational Linguistics. find our card
  39. Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, and Quoc V. Le. 2018a. Qanet: Combining local convolution with global self-attention for reading comprehension. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 -… find our card
  40. OpenReview.net. Nan Yu, Meishan Zhang, and Guohong Fu. 2018b. Transition-based neural RST parsing with implicit syntax features. In Proceedings of the 27th International Conference on Computational Linguistics, pages 559– 570, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  41. Zhuosheng Zhang, Junjie Yang, and Hai Zhao. 2020a. Retrospective reader for machine reading comprehension. find
  42. Zhuosheng Zhang, Hai Zhao, and Rui Wang. 2020b. Machine reading comprehension: The role of contextualized language models and beyond. ArXiv preprint, abs/2005.06249. — [arXiv:2005.06249](https://arxiv.org/abs/2005.06249) find

↑ back to top

This page in Markdown →