Elamur Research⌕
☰
home / papers / 2021 / Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

Paper · 2021 · Jiaao Chen and Diyi Yang

Summary

Chat summaries produced by neural models often omit key content, repeat themselves, or attribute actions to the wrong person. The authors argue this happens because dialogues are loosely organized and involve several speakers. They propose S-BART, a BART-based sequence-to-sequence model that makes two kinds of conversational structure explicit.

  • Discourse relation graph: links utterances through dependency-style discourse relations. A discourse parser trained on a human-annotated multi-party dialogue corpus predicts these relations.
  • Action graph: connects "WHO-DOING-WHAT" triples. These are extracted with OpenIE after first-person and second-person references are rewritten into speaker names.

Graph Attention Networks encode both graphs alongside a transformer utterance encoder. A multi-granularity decoder then attends to utterances, discourse structure and actions together, using ReZero-weighted cross-attention.

On SAMSum, S-BART outperforms state-of-the-art baselines in both automatic metrics and human judgments. It also transfers zero-shot to debate summarization (ADSC Corpus). The work shows that explicit linguistic structure can make dialogue summaries more succinct and more faithful about who did what. The code is public (GT-SALT/Structure-Aware-BART).

Key points

  • Discourse parser and graph statistics: The parser (Shi and Huang, 2019) uses 16 relation types from Asher et al. (2016). It reaches 0.775 F1 on link prediction and 0.557 F1 on relation classification. On SAMSum it yields 138,554 edges, about 8.48 per conversation. The most frequent relations are Question Answer Pair (21.5%) and Comment (19.3%).
  • Ablations: Real discourse graphs beat random graphs that have the same number of edges. Combining the two graphs in parallel works better than attending to them sequentially, which suggests the graphs provide complementary signals.
  • Zero-shot debate results: On ADSC, conversations contain far more action triples than SAMSum (37.20 vs 6.81). The available text reports large relative ROUGE gains over BART: 373.4% on ROUGE-2 and 82.2% on ROUGE-L. The ROUGE-1 figure is cut off in the extracted text.
  • Error analysis (819 SAMSum test dialogues): S-BART helps most when conversations have more discourse edges and action triples. Both S-BART and BART struggle on the most interaction-heavy cases.
  • ReZero weights: Initializing α at 1 works better than initializing it at 0. Action graphs receive larger learned α than discourse graphs.

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

 Institutions

🎓Georgia Institute of TechnologyAtlanta · United States69 works · 22,788 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 2Research subjects and languages the work is about.Discourse analysis · 394 worksSummarization · 159 works

Cite

Cite as Jiaao Chen and Diyi Yang. 2021. Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.naacl-main.109

@inproceedings{chen2021structure,
  title = {{Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs}},
  author = {Jiaao Chen and Diyi Yang},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2021},
  doi = {10.18653/v1/2021.naacl-main.109},
  url = {https://doi.org/10.18653/v1/2021.naacl-main.109}
}

References

54 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gabor Angeli, Melvin Jose Johnson Premkumar, and Christopher D. Manning. 2015. Leveraging linguistic structure for open domain information extraction. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Lang…
  2. 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.
  3. Thomas Bachlechner, Bodhisattwa Prasad Majumder, Huanru Henry Mao, Garrison W Cottrell, and Julian McAuley. 2020. Rezero is all you need: Fast convergence at large depth. arXiv preprint arXiv:2003.04887. story completion. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, p… find
  4. Jiaao Chen and Diyi Yang. 2020. Multi-view sequence-to-sequence models with conversational structure for abstractive dialogue summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4106–4118, Online. Association for Computational Lingu…
  5. Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, and Jingjing Liu. 2020. Multi-fact correction in abstractive text summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9320–9331, Online. Association for Computationa…
  6. Rotem Dror, Gili Baumer, Segev Shlomov, and Roi Reichart. 2018. The hitchhiker’s guide to testing statistical significance in natural language processing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1383–1392. find
  7. Angela Fan, Claire Gardent, Chloé Braud, and Antoine Bordes. 2019. Using local knowledge graph construction to scale seq2seq models to multi-document inputs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natura… find
  8. Xiachong Feng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2020. Incorporating commonsense knowledge into abstractive dialogue summarization via heterogeneous graph networks. arXiv preprint arXiv:2010.10044. find
  9. Patrick Fernandes, Miltiadis Allamanis, and Marc Brockschmidt. 2018. Structured neural summarization. In International Conference on Learning Representations. find
  10. Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. In Advances in Neural Information Processing Systems, pages 1171–1179. find
  11. Michel Galley. 2006. A skip-chain conditional random field for ranking meeting utterances by importance. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 364–372. find
  12. Trung Bui, Matthew Frampton, John Dowding, and Stanley Peters. 2009. Extracting decisions from multi-party dialogue using directed graphical models and semantic similarity. In Proceedings of the SIGDIAL 2009 Conference, pages 235–243, London, UK. Association for Computational Linguistics. find
  13. Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, and Rui Yan. 2020. From standard summarization to new tasks and beyond: Summarization with manifold information. arXiv preprint arXiv:2005.04684. — [arXiv:2005.04684](https://arxiv.org/abs/2005.04684) find
  14. Ziqiang Cao, Furu Wei, W. Li, and Sujian Li. 2018. Faithful to the original: Fact aware neural abstractive summarization. In AAAI. find
  15. Jiaao Chen, Jianshu Chen, and Zhou Yu. 2019. Incorporating structured commonsense knowledge in James Paul Gee. 2014. An introduction to discourse analysis: Theory and method. Routledge. find
  16. 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 statistics. In Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, page 605. Ass… find
  17. 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
  18. Vishal Gupta and Gurpreet Singh Lehal. 2010. A survey of text summarization extractive techniques. Journal of emerging technologies in web intelligence, 2(3):258–268. find
  19. Luyang Huang, Lingfei Wu, and Lu Wang. 2020a. Knowledge graph-augmented abstractive summarization with semantic-driven cloze reward. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5094– 5107, Online. Association for Computational Linguistics. find
  20. Shanshan Huang, Kenny Q. Zhu, Qianzi Liao, Libin Shen, and Yinggong Zhao. 2020b. Enhanced story representation by conceptnet for predicting story endings. In Proceedings of the 29th ACM International Conference on Information Knowledge Management, CIKM ’20, page 3277–3280, New York, NY, USA. Associa… find
  21. Paul A Kirschner, Simon J Buckingham-Shum, and Chad S Carr. 2012. Visualizing argumentation: Software tools for collaborative and educational sensemaking. Springer Science & Business Media. find
  22. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M. Rush. 2017. Opennmt: Open-source toolkit for neural machine translation.
  23. 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
  24. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the…
  25. 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…
  26. Chin-Yew Lin and Franz Josef Och. 2004. Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram 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 SIG… find
  27. H. Liu and P. Singh. 2004. Conceptnet — a practical commonsense reasoning tool-kit. BT Technology Journal, 22(4):211–226. find
  28. Yang Liu and Mirella Lapata. 2019. Text summarization with pretrained encoders. 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), pages 3721–3731. find
  29. 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
  30. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60, Baltimore, Ma…
  31. Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. 2020. On faithfulness and factuality in abstractive summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1906–1919, Online. Association for Computational Linguistics. find
  32. K. McKeown, Lokesh Shrestha, and Owen Rambow. 2007. Using question-answer pairs in extractive summarization of email conversations. In CICLing. find
  33. Amita Misra, Pranav Anand, Jean E. Fox Tree, and Marilyn Walker. 2015. Using summarization to discover argument facets in online idealogical dialog. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, page… find
  34. Beverly Moser. 2001. An introduction to discourse analysis. theory and method. find
  35. Gabriel Murray, S. Renals, and J. Carletta. 2005. Extractive summarization of meeting recordings. In INTERSPEECH. find
  36. Gabriel Murray, Steve Renals, Jean Carletta, and Johanna Moore. 2006. Incorporating speaker and discourse features into speech summarization. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 367– 374, New York City, USA. Association for Computational Li… find
  37. Shashi Narayan, Shay B Cohen, and Mirella Lapata. 2018. Ranking sentences for extractive summarization with reinforcement learning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers…
  38. Romain Paulus, Caiming Xiong, and Richard Socher. 2018. A deep reinforced model for abstractive summarization. In International Conference on Learning Representations.
  39. Kechen Qin, Lu Wang, and Joseph Kim. 2017. Joint modeling of content and discourse relations in dialogues. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 974–984. find
  40. 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
  41. 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
  42. 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
  43. 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 Asso… find
  44. 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
  45. Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, and Fei Liu. 2020. The ucf podcast summarization system at trec 2020. arXiv preprint arXiv:2011.04132. — [arXiv:2011.04132](https://arxiv.org/abs/2011.04132) find
  46. Matthew Stone, Una Stojnic, and Ernest Lepore. 2013. Situated utterances and discourse relations. In Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013)–Short Papers, pages 390–396. find
  47. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008.
  48. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations. find
  49. Lu Wang and Claire Cardie. 2013. Domain-independent abstract generation for focused meeting summarization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1395– 1405. find
  50. Jiacheng Xu, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Discourse-aware neural extractive text summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5021–5031, Online. Association for Computational Linguistics.
  51. Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter J Liu. 2019. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. arXiv preprint arXiv:1912.08777.
  52. 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
  53. Chenguang Zhu, William Hinthorn, Ruochen Xu, Qing kai Zeng, Michael Zeng, Xuedong Huang, and Meng Jiang. 2020a. Boosting factual correctness of abstractive summarization with knowledge graph. ArXiv, abs/2003.08612. — [arXiv:2003.08612](https://arxiv.org/abs/2003.08612) find
  54. Chenguang Zhu, Ruochen Xu, Michael Zeng, and Xuedong Huang. 2020b. A hierarchical network for abstractive meeting summarization with cross-domain pretraining. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online. Association for Computational Ling… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chen-2021-structure-aware-abstractive-conversation-summarization/