Abstract
Dialogue summarization aims to distill a given conversation into a brief and focused summary. The challenge lies in the diverse perspectives of participants and the frequent shifts in topics throughout the dialogue. These factors make it difficult to extract and highlight the most significant information effectively. To tackle this challenge, we introduce a novel topic segmentation method that assigns distinct topics to dialogue segments while accounting for their importance and influence within the entire conversation. Our method's performance has been validated on two public benchmark datasets, CSDS and SAMSUM, demonstrating significant improvements in accuracy and coherence. The results show that our approach not only captures the essential content of dialogues more precisely but also enhances the overall quality and coverage of the summaries. This work provides a fresh approach to dialogue summarization and highlights its potential for practical application.
Publisher
Century Science Publishing Co
Reference35 articles.
1. "[1]T. Berg-Kirkpatrick, D. Gillick, and D. Klein, “Jointly learning to extract and compress,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (D. Lin, Y. Matsumoto, and R. Mihalcea, eds.), (Portland, Oregon, USA), pp. 481–490, Association for Computational Linguistics, June 2011.
2. K. Filippova, E. Alfonseca, C. A. Colmenares, L. Kaiser, and O. Vinyals, “Sentence compression by deletion with LSTMs,” in Proceedings of the 2015 Conferenceon Empirical Methods in Natural Language Processing (L. M`arquez, C. CallisonBurch, and J. Su, eds.), (Lisbon, Portugal), pp. 360–368, Association for Computational Linguistics, Sept. 2015.
3. H. Jing and K. R. McKeown, “Cut and paste based text summarization,” in 1st Meeting of the North American Chapter of the Association for Computational Linguistics, 2000.
4. M. Banko, V. O. Mittal, and M. J. Witbrock, “Headline generation based on statistical translation,” in Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, (Hong Kong), pp. 318–325, Association for Computational Linguistics, Oct. 2000.
5. S. Chopra, M. Auli, and A. M. Rush, “Abstractive sentence summarization with attentive recurrent neural networks,” in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (K. Knight, A. Nenkova, and O. Rambow, eds.), (San Diego, California), pp. 93–98, Association for Computational Linguistics, June 2016.