Elamur Research⌕
☰
home / papers / 2024 / Dialogue Discourse Parsing as Generation: A Sequence-to-Sequence LLM-based Approach

Dialogue Discourse Parsing as Generation: A Sequence-to-Sequence LLM-based Approach

Summary

The paper tackles dialogue discourse parsing (DDP): linking the Elementary Discourse Units of a multi-party conversation and labelling each link with a rhetorical relation such as Elaboration or QA-pair. Earlier systems use encoder-only models like BERT or RoBERTa with custom decoders, usually MST-based, so they can only produce trees. Prompting LLMs directly also performs poorly on this task. The authors instead treat parsing as text-to-text generation. They fine-tune an unmodified encoder-decoder LLM (mainly T0-3B) to read the dialogue and output its structure as linearized text. They test several output formats: a near-natural-language template, a TANL-inspired augmented format, and a "focused" scheme.

They build two systems:

  • Seq2Seq-DDP parses the whole dialogue in one pass.
  • Seq2Seq-DDP+Transition borrows from transition-based dependency parsing. It handles one utterance per step, using a sliding window of prior context.

On STAC and Molweni, the transition variant sets a new state of the art on Molweni. It also copes better with long dialogues. Because generation is not restricted to trees, both systems can output graph-shaped structures (DAGs), which matters for SDRT-style annotation.

Key points

  • Datasets are STAC and Molweni. Code is released at github.com/chuyuanli/Seq2Seq-DDP.
  • Model comparison on the STAC dev set (Link F1 / Full F1, natural scheme):
    • T0-3B: 69.2 / 50.2
    • Flan-T5-xl: 68.5 / 50.4
    • T5-3B: 60.7 / 40.5
  • Nodes with multiple incoming edges are rare: about 5% of nodes and under 7% of links in STAC, and none in Molweni. The focused scheme in the transition system identifies them with about 13% precision; other schemes reach about 10%.
  • Performance falls as dialogues get longer for both systems, but the transition-based models hold up better across both datasets.
  • Speed trade-off on STAC dev: the one-pass system needs about 2.5 s per document. The transition system takes about 1.8 s per step, roughly 20 s per document, but achieves higher F1.

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 · Dependency parsing

Cited by

7 papers of our library cite it (of the 140673 whose bibliographies we read).

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.sigdial-1.1

@inproceedings{li2024dialogue,
  title = {{Dialogue Discourse Parsing as Generation: A Sequence-to-Sequence LLM-based Approach}},
  author = {Li, Chuyuan and Yin, Yuwei and Carenini, Giuseppe},
  booktitle = {Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  year = {2024},
  doi = {10.18653/v1/2024.sigdial-1.1},
  url = {https://doi.org/10.18653/v1/2024.sigdial-1.1}
}

References

52 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Stergos Afantenos, Nicholas Asher, Farah Benamara, Anaıs Cadilhac, Cedric Dégremont, Pascal Denis, Markus Guhe, Simon Keizer, Alex Lascarides, Oliver Lemon, et al. 2012. Modelling strategic conversation: model, annotation design and corpus. In Proceedings of the 16th Workshop on the Semantics and Pr… find
  2. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712. find our card
  3. 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
  4. Chunkit Chan, Jiayang Cheng, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, and Yangqiu Song. 2023. Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations. arXiv preprint arXiv:2304.14827. find our card
  5. 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
  6. Ta-Chung Chi and Alexander Rudnicky. 2022. Structured dialogue discourse parsing. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 325–335. find our card
  7. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language Nicholas Asher and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press. modeling w… find
  8. Chris Hokamp and Qun Liu. 2017. Lexically constrained decoding for sequence generation using grid beam search. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1535–1546, Vancouver, Canada. Association for Computational Linguis… find our card
  9. Yoeng-Jin Chu. 1965. On the shortest arborescence of a directed graph. Scientia Sinica, 14:1396–1400. find
  10. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416. find
  11. Matthew A Jaro. 1989. Advances in record-linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Association, 84(406):414–420. find
  12. 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 Language Technologies,… find
  13. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199– 22213. find our card
  14. Chuyuan Li, Chloé Braud, Maxime Amblard, and Giuseppe Carenini. 2024. Discourse relation prediction and discourse parsing in dialogues with minimal supervision. In Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024), pages 161–176, St. Julians, Malta. Association for… find our card
  15. Jack Edmonds et al. 1967. Optimum branchings. Journal of Research of the national Bureau of Standards B, 71(4):233–240. find
  16. Chuyuan Li, Patrick Huber, Wen Xiao, Maxime Amblard, Chloe Braud, and Giuseppe Carenini. 2023a. Discourse structure extraction from pre-trained and fine-tuned language models in dialogues. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2562–2579, Dubrovnik, Croatia. A… find
  17. Jason M. Eisner. 1996. Three new probabilistic models for dependency parsing: An exploration. In COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics. find our card
  18. Xiachong Feng, Xiaocheng Feng, and Bing Qin. 2021. A survey on dialogue summarization: Recent advances and new frontiers. arXiv preprint arXiv:2107.03175. — [arXiv:2107.03175](https://arxiv.org/abs/2107.03175) find
  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. Deep Ganguli, Danny Hernandez, Liane Lovitt, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova Dassarma, Dawn Drain, Nelson Elhage, et al. 2022. Predictability and surprise in large generative models. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, page… find
  21. Jiaqi Li, Ming Liu, Yuxin Wang, Daxing Zhang, and Bing Qin. 2023b. A speaker-aware multiparty dialogue discourse parser with heterogeneous graph neural network. Cognitive Systems Research, 79:15– 23. find
  22. Ivan Habernal, Omnia Zayed, and Iryna Gurevych. 2016. C4Corpus: Multilingual web-size corpus with free license. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 914–922, Portorož, Slovenia. European Language Resources Association (ELRA). find
  23. Jiwei Li, Rumeng Li, and Eduard Hovy. 2014. Recursive deep models for discourse parsing. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2061–2069. find our card
  24. Han He and Jinho D Choi. 2023. Unleashing the true potential of sequence-to-sequence models for sequence tagging and structure parsing. Transactions of the Association for Computational Linguistics, 11:582– 599. find
  25. Wei Li, Luyao Zhu, Wei Shao, Zonglin Yang, and Erik Cambria. 2023c. Task-aware self-supervised framework for dialogue discourse parsing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14162–14173, Singapore. Association for Computational Linguistics. find our card
  26. Yuchen He, Zhuosheng Zhang, and Hai Zhao. 2021. Multi-tasking dialogue comprehension with discourse parsing. In Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, pages 551–561, Shanghai, China. Association for Computational Lingustics. find our card
  27. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. find
  28. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. find
  29. Jérémy Perret, Stergos Afantenos, Nicholas Asher, and Mathieu Morey. 2016. Integer linear programming for discourse parsing. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 99–109, San Diego, Cal… find our card
  30. 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, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics. find our card
  31. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67. find
  32. Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In International Conference on Learning Representations. find
  33. Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. 2015. The Ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 285–294, Prague, Czech Republi… find our card
  34. Subendhu Rongali, Luca Soldaini, Emilio Monti, and Wael Hamza. 2020. Don’t parse, generate! A sequence to sequence architecture for task-oriented semantic parsing. In WWW ’20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, pages 2962– 2968. ACM / IW3C2. find
  35. Xinbei Ma, Zhuosheng Zhang, and Hai Zhao. 2023. Enhanced speaker-aware multi-party multi-turn dialogue comprehension. IEEE/ACM Transactions on Audio, Speech, and Language Processing. find
  36. Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal V. Nayak, Debajyoti Datta, Jonatha… find our card
  37. Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, and Manabu Okumura. 2024. Can we obtain significant success in RST discourse parsing by using large language models? In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers),… find our card
  38. Philippe Muller, Stergos Afantenos, Pascal Denis, and Nicholas Asher. 2012. Constrained decoding for text-level discourse parsing. In Proceedings of COLING 2012, pages 1883–1900, Mumbai, India. find our card
  39. The COL-ING 2012 Organizing Committee. find
  40. 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, volume 33, pages 7007–7014. find
  41. Noriki Nishida and Yuji Matsumoto. 2022. Out-of-domain discourse dependency parsing via bootstrapping: An empirical analysis on its effectiveness and limitation. Transactions of the Association for Computational Linguistics, 10:127–144. find
  42. Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053. find
  43. Joakim Nivre. 2003. An efficient algorithm for projective dependency parsing. In Proceedings of the Eighth International Conference on Parsing Technologies, pages 149–160, Nancy, France. find our card
  44. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adri Garriga-Alonso, et al. 2023. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. Transactions on machine learning rese… find our card
  45. Joakim Nivre. 2008. Algorithms for deterministic incremental dependency parsing. Computational Linguistics, 34(4):513–553. find our card
  46. Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cícero Nogueira dos Santos, Bing Xiang, and Stefano Soatto. 2021. Structured prediction as translation between augmented natural languages. In 9th International Conference on Learning Representations, ICLR… find
  47. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. find
  48. Gorka Urbizu, Ander Soraluze, and Olatz Arregi. 2020. Sequence to sequence coreference resolution. In Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, pages 39–46, Barcelona, Spain (online). Association for Computational Linguistics. find
  49. Gyeongju, Republic of Korea. International Committee on Computational Linguistics. find
  50. Wenzheng Zhang, Sam Wiseman, and Karl Stratos. 2023. Seq2seq is all you need for coreference resolution. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11493–11504, Singapore. Association for Computational Linguistics. find our card
  51. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. Advances in neural information processing systems, 28. find
  52. A Ante Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, and Jinsong Su. 2021a. A structure self-aware model for discourse parsing on multi-party dialogues. In Proceedings of the Thirtieth International Conference on International Joint Conferences on Artificial Intelligence. find

↑ back to top