Topic-Oriented Dialogue Summarization
Authors: 
Haitao Lin, Junnan Zhu, Lu Xiang, Feifei Zhai, Yu Zhou, Jiajun Zhang, Chengqing ZongAuthors Info & Claims
Pages 1797 - 1810
Abstract
A multi-turn dialogue often contains multiple discussion topics. In several scenarios (e.g., customer service dispute, public opinion monitoring), people are only interested in the gist of a specific topic in the dialogue. Therefore, we propose a novel summarization task, i.e., Topic-Oriented Dialogue Summarization (TODS). Given a dialogue with a topic label, TODS aims to produce a summary covering the main content of the given topic in the dialogue. To model the relationship between dialogues and topics, three key abilities are needed for TODS: (1) Learning the semantic information of different topics. (2) Locating the topic-related content in the dialogue. (3) Distinguishing summaries for different topics in the same dialogue. Thus, we propose three topic-related auxiliary tasks to make the summarization model learn the three abilities above. First, the topic identification task aims at generating all the topics in the dialogue. Second, the topic attention restriction task tries to constrain the attention distribution on topic-related utterances. Third, the topic summary distinguishing task focuses on increasing the difference of summaries for different topics in the same dialogue. Experimental results on two public TODS datasets show that all auxiliary tasks are critical for TODS and help generate high-quality summaries. We also point out the expansions and challenges in TODS for future research.
References
[1]
C. Zong, R. Xia, and J. Zhang, Text Data Mining. vol. 711, Berlin, Germany: Springer, 2021.
[2]
M. Soni et al., “An empirical study of topic transition in dialogue,” in Proc. 3rd Workshop Comput. Approaches Discourse, 2022, pp. 92–99.
[3]
J. He, W. Kryściński, B. McCann, N. Rajani, and C. Xiong, “CTRLsum: Towards generic controllable text summarization,” 2020, arXiv:2012.04281.
[4]
A. Fan, D. Grangier, and M. Auli, “Controllable abstractive summarization,” in Proc. 2nd Workshop Neural Mach. Transl. Gener., 2018, pp. 45–54.
[5]
H. Li, J. Zhu, J. Zhang, C. Zong, and X. He, “Keywords-guided abstractive sentence summarization,” in Proc. 34th AAAI Conf. Artif. Intell., 2020, vol. 34, pp. 8196–8203.
[6]
H. Lin et al., “CSDS: A fine-grained chinese dataset for customer service dialogue summarization,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2021, pp. 4436–4451.
[7]
Y. Chen, Y. Liu, L. Chen, and Y. Zhang, “DialogSum: A real-life scenario dialogue summarization dataset,” in Proc. Findings Assoc. Comput. Linguistics, 2021, pp. 5062–5074.
[8]
M. Lewis et al., “BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,” in Proc. 58th Annu. Meeting Assoc. Comput. Linguistics, 2020, pp. 7871–7880.
[9]
I. McCowan et al., “The AMI meeting corpus,” in Proc. Measuring Behav., 5th Int. Conf. Methods Techn. Behav. Res., 2005, pp. 137–140.
[10]
A. Janin et al., “The ICSI meeting corpus,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2003, vol. 1, pp. 364–367.
[11]
C. Zhu, R. Xu, M. Zeng, and X. Huang, “A hierarchical network for abstractive meeting summarization with cross-domain pretraining,” in Proc. Findings Assoc. Comput. Linguistics, 2020, pp. 194–203.
[12]
B. Gliwa, I. Mochol, M. Biesek, and A. Wawer, “SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization,” in Proc. 2nd Workshop New Front. Summarization, 2019, pp. 70–79.
[13]
X. Feng, X. Feng, L. Qin, B. Qin, and T. Liu, “Language model as an annotator: Exploring DialoGPT for dialogue summarization,” in Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process., 2021, vol. 1, pp. 1479–1491.
[14]
Z. Liu and N. Chen, “Controllable neural dialogue summarization with personal named entity planning,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2021, pp. 92–106. [Online]. Available: https://aclanthology.org/2021.emnlp-main.8
[15]
Z. Liu, A. Ng, S. Lee, A. T. Aw, and N. F. Chen, “Topic-aware pointer-generator networks for summarizing spoken conversations,” in Proc. IEEE Autom. Speech Recognit. Understanding Workshop, 2019, pp. 814–821.
[16]
Y. Song, Y. Tian, N. Wang, and F. Xia, “Summarizing medical conversations via identifying important utterances,” in Proc. 28th Int. Conf. Comput. Linguistics, 2020, pp. 717–729.
[17]
K. Krishna, S. Khosla, J. Bigham, and Z. C. Lipton, “Generating SOAP notes from doctor-patient conversations using modular summarization techniques,” in Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process., 2021, vol. 1, pp. 4958–4972.
[18]
C. Liu, P. Wang, J. Xu, Z. Li, and J. Ye, “Automatic dialogue summary generation for customer service,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2019, pp. 1957–1965.
[19]
G. Feigenblat, C. Gunasekara, B. Sznajder, S. Joshi, D. Konopnicki, and R. Aharonov, “TWEETSUMM - A dialog summarization dataset for customer service,” in Proc. Findings Assoc. Comput. Linguistics, 2021, pp. 245–260.
[20]
H. Lin, J. Zhu, L. Xiang, Y. Zhou, J. Zhang, and C. Zong, “Other roles matter! enhancing role-oriented dialogue summarization via role interactions,” in Proc. 60th Annu. Meeting Assoc. Comput. Linguistics, 2022, vol. 1, pp. 2545–2558. [Online]. Available: https://aclanthology.org/2022.acl-long.182
[21]
L. Zhao, W. Xu, and J. Guo, “Improving abstractive dialogue summarization with graph structures and topic words,” in Proc. 28th Int. Conf. Comput. Linguistics, 2020, pp. 437–449.
[22]
J. Chen and D. Yang, “Multi-view sequence-to-sequence models with conversational structure for abstractive dialogue summarization,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2020, pp. 4106–4118.
[23]
Y. Zou et al., “Topic-oriented spoken dialogue summarization for customer service with saliency-aware topic modeling,” in Proc. AAAI Conf. Artif. Intell., 2021, vol. 35, pp. 14665–14673.
[24]
J. Liu et al., “Topic-aware contrastive learning for abstractive dialogue summarization,” in Proc. Findings Assoc. Comput. Linguistics, 2021, pp. 1229–1243.
[25]
L. Frermann and A. Klementiev, “Inducing document structure for aspect-based summarization,” in Proc. 57th Annu. Meeting Assoc. Comput. Linguistics, 2019, pp. 6263–6273.
[26]
B. Tan, L. Qin, E. Xing, and Z. Hu, “Summarizing text on any aspects: A knowledge-informed weakly-supervised approach,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2020, pp. 6301–6309.
[27]
R. K. Amplayo, S. Angelidis, and M. Lapata, “Aspect-controllable opinion summarization,” in Proc. Conf. Empirical Methods Natural Lang. Process., 2021, pp. 6578–6593.
[28]
O. Ahuja, J. Xu, A. Gupta, K. Horecka, and G. Durrett, “ASPECTNEWS: Aspect-oriented summarization of news documents,” in Proc. 60th Annu. Meeting Assoc. Comput. Linguistics, Dublin, Ireland, 2022, vol. 1, pp. 6494–6506.
[29]
M. Hu and B. Liu, “Mining and summarizing customer reviews,” in Proc. 10th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, 2004, pp. 168–177.
[30]
A.-M. Popescu and O. Etzioni, “Extracting product features and opinions from reviews,” in Proc. Conf. Hum. Lang. Technol. Empirical Methods Natural Lang. Process., 2005, pp. 339–346.
[31]
M. Zhong et al., “QMSum: A new benchmark for query-based multi-domain meeting summarization,” in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol., 2021, pp. 5905–5921.
[32]
P. J. Liu et al., “Generating wikipedia by summarizing long sequences,” in Proc. Int. Conf. Learn. Representations, 2018. [Online]. Available: https://openreview.net/forum?id=Hyg0vbWC-
[33]
S. Kulkarni, S. Chammas, W. Zhu, F. Sha, and E. Ie, “AQuaMuSe: Automatically generating datasets for query-based multi-document summarization,” 2020, arXiv:2010.12694.
[34]
L. Huang, S. Cao, N. Parulian, H. Ji, and L. Wang, “Efficient attentions for long document summarization,” in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol., 2021, pp. 1419–1436.
[35]
Y. Zhang et al., “Summ\(^\mathrm{N}\): A multi-stage summarization framework for long input dialogues and documents,” in Proc. 60th Annu. Meeting Assoc. Comput. Linguistics, 2022, vol. 1, pp. 1592–1604.
[36]
Z. Mao et al., “DYLE: Dynamic latent extraction for abstractive long-input summarization,” in Proc. 60th Annu. Meeting Assoc. Comput. Linguistics, 2022, vol. 1, pp. 1687–1698.
[37]
J. Vig, A. R. Fabbri, W. Kryściński, C.-S. Wu, and W. Liu, “Exploring neural models for query-focused summarization,” in Proc. Findings Assoc. Comput. Linguistics, 2022, pp. 1455–1468.
[38]
Y. Liu, Y. Wan, L. He, H. Peng, and P. S. Yu, “KG-BART: Knowledge graph-augmented BART for generative commonsense reasoning,” in Proc. 35th AAAI Conf. Artif. Intell., 2021, vol. 35, pp. 6418–6425.
[39]
H. Lin, L. Xiang, Y. Zhou, J. Zhang, and C. Zong, “Augmenting slot values and contexts for spoken language understanding with pretrained models,” in Proc. Interspeech, 2021, pp. 4703–4707.
[40]
X. Feng, X. Feng, and B. Qin, “A survey on dialogue summarization: Recent advances and new frontiers,” in Proc. 31st Int. Joint Conf. Artif. Intell., 2022, pp. 5453–5460.
[41]
Y. Shao et al., “CPT: A pre-trained unbalanced transformer for both chinese language understanding and generation,” 2021, arXiv:2109.05729.
[42]
C.-Y. Lin and E. Hovy, “Manual and automatic evaluation of summaries,” in Proc. Workshop Autom. Summarization Phildadelphia, 2002, pp. 45–51.
[43]
K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, “Bleu: A method for automatic evaluation of machine translation,” in Proc. 40th Annu. Meeting Assoc. Comput. Linguistics, 2002, pp. 311–318.
[44]
T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, “BERTscore: Evaluating text generation with BERT,” in Proc. 8th Int. Conf. Learn. Representations, 2020. [Online]. Available: https://openreview.net/forum?id=SkeHuCVFDr
[45]
W. Zhao, M. Peyrard, F. Liu, Y. Gao, C. M. Meyer, and S. Eger, “MoverScore: Text generation evaluating with contextualized embeddings and earth mover distance,” in Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process., 2019, pp. 563–578.
Index Terms
- Topic-Oriented Dialogue Summarization
Index terms have been assigned to the content through auto-classification.
Recommendations
Topic-driven reader comments summarization
CIKM '12: Proceedings of the 21st ACM international conference on Information and knowledge managementReaders of a news article often read its comments contributed by other readers. By reading comments, readers obtain not only complementary information about this news article but also the opinions from other readers. However, the existing ranking ...
Topic analysis for topic-focused multi-document summarization
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementTopic-focused multi-document summarization has been a challenging task because the created summary is required to be biased to the given topic or query. Existing methods consider the given topic as a single coarse unit and then directly incorporate the ...
Entity-centric topic-oriented opinion summarization in twitter
KDD '12: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data miningMicroblogging services, such as Twitter, have become popular channels for people to express their opinions towards a broad range of topics. Twitter generates a huge volume of instant messages (i.e. tweets) carrying users' sentiments and attitudes every ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
2329-9290 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 04 May 2023
Published in TASLP Volume 31
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 12Total Downloads
- Downloads (Last 12 months)12
- Downloads (Last 6 weeks)1
Reflects downloads up to 25 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in