Elamur Research⌕
☰
home / papers / 2020 / Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization

Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization

Summary

Most summarization research targets single-author, well-organized texts such as news. Chat dialogues are messier: key facts are spread across turns by different speakers and mixed with fillers, abbreviations and emoticons. Chen and Yang tackle abstractive dialogue summarization by giving the model explicit conversational structure. Each chat is automatically segmented from several perspectives:

  • a topic view, using C99 segmentation over Sentence-BERT utterance embeddings;
  • a stage view, using an HMM with ordered stages (openings, intentions, discussions, conclusions);
  • generic global and discrete (per-utterance) views.

A conversation encoder processes each view separately. A multi-view decoder first weighs the views, then attends to tokens inside them. On the SAMSum corpus, the BART-based version outperformed earlier state-of-the-art systems in both automatic metrics and human evaluation. A manual analysis of 100 test dialogues shows that omitted content and wrong speaker attribution remain open problems. The work matters because it shows that cheap, unsupervised structure cues can improve chat summaries without expert discourse annotation.

Key points

  • Four conversation views are combined: topic (C99 + Sentence-BERT), stage (HMM with monotonic stage transitions), global, and discrete. The best model is Multi-view BART with topic + stage views.
  • Evaluation uses SAMSum (Gliwa et al., 2019). Code is released at github.com/GT-SALT/Multi-View-Seq2Seq.
  • In 100 sampled test dialogues, the difficulties encountered most often were resolving who or what is being referred to (33%) and shifts in speaker roles or in the language used (30%). Generic, simple chats were the easiest to summarize.
  • The most common error type was missing information (37%), followed by incorrect reasoning (24%), which had the lowest ROUGE-2. Improper gendered pronouns were rare (6%) but sharply lowered ROUGE-1/2.
  • Wrong speaker references co-occurred strongly with coreference difficulties. Future work targets supervised segmentation and dialogue-act structure.

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: Natural language processing

Cited by

85 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 81 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.emnlp-main.336

@inproceedings{chen2020multi,
  title = {{Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization}},
  author = {Chen, Jiaao and Yang, Diyi},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.336},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.336}
}

References

51 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tim Althoff, Kevin Clark, and Jure Leskovec. 2016. Large-scale analysis of counseling conversations: An application of natural language processing to mental health. Transactions of the Association for Computational Linguistics, 4:463–476. find
  2. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. find
  3. Ziqiang Cao, Furu Wei, Wenjie Li, and Sujian Li. 2018. Faithful to the original: Fact aware neural abstractive summarization. In AAAI. find
  4. Danqi Chen, Jason Bolton, and Christopher D. Manning. 2016. A thorough examination of the CNN/daily mail reading comprehension task. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2358–2367, Berlin, Germany. Association for C… find our card
  5. Yen-Chun Chen and Mohit Bansal. 2018. Fast abstractive summarization with reinforce-selected sentence rewriting. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 675–686, Melbourne, Australia. Association for Computational Ling… find our card
  6. Freddy Y. Y. Choi. 2000. Advances in domain independent linear text segmentation. In 1st Meeting of the North American Chapter of the Association for Computational Linguistics. find our card
  7. Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, and Nazli Goharian. 2018. A discourse-aware attention model for abstractive summarization of long documents. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational… find our card
  8. Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir Radev. 2019. Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. find our card
  9. Tobias Falke, Christian M Meyer, and Iryna Gurevych. 2017. Concept-map-based multi-document summarization using concept coreference resolution and global importance optimization. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages… find our card
  10. Michel Galley, Kathleen R. McKeown, Eric Fosler-Lussier, and Hongyan Jing. 2003. Discourse segmentation of multi-party conversation. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 562–569, Sapporo, Japan. Association for Computational Linguistics. find our card
  11. Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, and Rui Yan. 2020. From standard summarization to new tasks and beyond: Summarization with manifold information. find
  12. Bogdan Gliwa, Iwona Mochol, Maciej Biesek, and Aleksander Wawer. 2019. SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 70–79, Hong Kong, China. Association for Computational Linguistics. find
  13. Chih-Wen Goo and Yun-Nung Chen. 2018. Abstractive dialogue summarization with sentence-gated modeling optimized by dialogue acts. 2018 IEEE Spoken Language Technology Workshop (SLT). find
  14. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput., 9(8):1735–1780. find
  15. Axel Honneth, Hans Joas, et al. 1988. Social action and human nature. CUP Archive. find
  16. Peter Jackson and Isabelle Moulinier. 2007. Natural language processing for online applications: Text retrieval, extraction and categorization, volume 5. John Benjamins Publishing. find
  17. Shafiq Joty, Giuseppe Carenini, Gabriel Murray, and Raymond T. Ng. 2010. Exploiting conversation structure in unsupervised topic segmentation for emails. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 388–398, Cambridge, MA. Association for Computati… find
  18. Shafiq Joty and Enamul Hoque. 2016. Speech act modeling of written asynchronous conversations with task-specific embeddings and conditional structured models. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1746–1756. find our card
  19. Grant H Kester. 2004. Conversation pieces: Community and communication in modern art. Univ of California Press. find
  20. Terry K Koo and Mae Y Li. 2016. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. Journal of chiropractic medicine, 15(2):155–163. find
  21. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. find our card
  22. Jing Li, Aixin Sun, and Shafiq R Joty. 2018. Segbot: A generic neural text segmentation model with pointer network. In IJCAI, pages 4166–4172. find
  23. Jiwei Li, Xinlei Chen, Eduard Hovy, and Dan Jurafsky. 2016. Visualizing and understanding neural models in NLP. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 681–691, San Diego, California. Ass… find our card
  24. Manling Li, Lingyu Zhang, Heng Ji, and Richard J. Radke. 2019. Keep meeting summaries on topic: Abstractive multi-modal meeting summarization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2190–2196, Florence, Italy. Association for Computational L… find
  25. Chin-Yew Lin and Franz Josef Och. 2004. Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, page 605. Association for Computational Linguistics. find our card
  26. Chunyi Liu, Peng Wang, Jiang Xu, Zang Li, and Jieping Ye. 2019a. Automatic dialogue summary generation for customer service. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD19, page 1957–1965, New York, NY, USA. Association for Computing Machin… find
  27. Peter J. Liu*, Mohammad Saleh*, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam Shazeer. 2018. Generating wikipedia by summarizing long sequences. In International Conference on Learning Representations. find our card
  28. Yang Liu and Mirella Lapata. 2019. Text summarization with pretrained encoders. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). find
  29. Zhengyuan Liu and Nancy Chen. 2019. Reading turn by turn: Hierarchical attention architecture for spoken dialogue comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5460–5466, Florence, Italy. Association for Computational Linguistics. find
  30. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). find
  31. Zhengyuan Liu, Angela Ng, Sheldon Lee, Ai Ti Aw, and Nancy F. Chen. 2019b. Topic-aware pointer-generator networks for summarizing spoken conversations. 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). find
  32. Alan Ritter, Colin Cherry, and Bill Dolan. 2010. Unsupervised modeling of twitter conversations. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 172–180, Los Angeles, California. Association for Computat… find our card
  33. Elijah Mayfield, David Adamson, and Carolyn Penstein Rosé. 2012. Hierarchical conversation structure prediction in multi-party chat. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 60–69, Seoul, South Korea. Association for Computational Ling… find
  34. Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, Çağlar Gu̇lçehre, and Bing Xiang. 2016. Abstractive text summarization using sequence-to-sequence RNNs and beyond. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pages 280–290, Berlin, Germany. Associatio… find
  35. Nikola I. Nikolov, Michael Pfeiffer, and Richard H. R. Hahnloser. 2018. Data-driven summarization of scientific articles. CoRR, abs/1804.08875. — [arXiv:1804.08875](https://arxiv.org/abs/1804.08875) find
  36. Tatsuro Oya and Giuseppe Carenini. 2014. Extractive summarization and dialogue act modeling on email threads: An integrated probabilistic approach. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIG-DIAL), pages 133–140. find our card
  37. Michael J. Paul. 2012. Mixed membership Markov models for unsupervised conversation modeling. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 94–104, Jeju Island, Korea. Association for Computational L… find
  38. Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 379–389, Lisbon, Portugal. Association for Computational Linguistics. find
  39. Harvey Sacks, Emanuel A Schegloff, and Gail Jefferson. 1978. A simplest systematics for the organization of turn taking for conversation. In Studies in the organization of conversational interaction, pages 7– 55. Elsevier. find
  40. Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer-generator networks. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). find
  41. Guokan Shang, Wensi Ding, Zekun Zhang, Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis, and Jean-Pierre Lorré. 2018. Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. In Proceedings of the 56th Annual Meeting of the Ass… find
  42. Felix Wu, Angela Fan, Alexei Baevski, Yann Dauphin, and Michael Auli. 2019. Pay less attention with lightweight and dynamic convolutions. In International Conference on Learning Representations. find our card
  43. Romain Paulus, Caiming Xiong, and Richard Socher. 2018. A deep reinforced model for abstractive summarization. In International Conference on Learning Representations. find our card
  44. Wen Xiao and Giuseppe Carenini. 2019. Extractive summarization of long documents by combining global and local context. In EMNLP/IJCNLP. find
  45. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog, 1(8):9. find
  46. Weiwei Zhang, Jackie Chi Kit Cheung, and Joel Oren. 2019. Generating character descriptions for automatic summarization of fiction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7476–7483. find
  47. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. find
  48. Zhou Zhao, Haojie Pan, Changjie Fan, Yan Liu, Linlin Li, Min Yang, and Deng Cai. 2019. Abstractive meeting summarization via hierarchical adaptive segmental network learning. In The World Wide Web Conference, WWW ’19, page 3455–3461, New York, NY, USA. Association for Computing Machinery. find
  49. Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, and Meng Jiang. 2020a. Boosting factual correctness of abstractive summarization. find
  50. Chenguang Zhu, Ruochen Xu, Michael Zeng, and Xuedong Huang. 2020b. End-to-end abstractive summarization for meetings. *Figure 6: Attention weights distribution for stage view and topic view in the multi-view model.* 330 595 158 621 446 320 208 69 254 364 617 741 15 172 793 493 358 717 519 136 find
  51. Henghui Zhu, Feng Nan, Zhiguo Wang, Ramesh Nallapati, and Bing Xiang. 2019. Who did they respond to? conversation structure modeling using masked hierarchical transformer. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chen-2020-multi-view-sequence-sequence-models/