Abstract
Dialogue rewriting aims to reconstruct the incomplete utterance from dialogue history. It is a challenge task due to the frequent phenomena of coreference and ellipses in dialogue. Although the conventional encoder-decoder architecture has shown the effectiveness for dialogue rewriting, there are still two issues should be addressed. Firstly, the objects referred to or omitted are usually mentions, represented as spans. So the traditional word-by-word copy mechanism, which is widely used in current models, can lead to incompletion, repetition and disorder problems. Secondly, words in dialogue history and common vocabulary list have different effects on rewriting the current utterance. Intuitively, semantically and cohesively matched spans are more important. In this paper, we propose a novel Gated Span-level Copy Mechanism (GSCM) that aims to retrieve the omitted or co-referred spans contained in history dialogue and recover them for the incomplete utterance. The experimental results on the CamRest676 and RiSAWOZ corpora show that our GSCM can significantly improve the performance of dialogue rewriting.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings, pp. 1–15 (2015)
Grave, E., Bojanowski, P., Gupta, P., Joulin, A., Mikolov, T.: Learning word vectors for 157 languages. In: Calzolari, N., et al. (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, 7–12 May 2018, pp. 1–5. European Language Resources Association (ELRA) (2018)
Gu, J., Lu, Z., Li, H., Li, V.O.K.: Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, 7–12 August 2016, Berlin, Germany, Volume 1: Long Papers, pp. 1631–1640. The Association for Computer Linguistics (2016)
Ji, Z., Lu, Z., Li, H.: An information retrieval approach to short text conversation. arXiv:abs/1408.6988 (2014)
Kumar, V., Joshi, S.: Non-sentential question resolution using sequence to sequence learning. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, Japan, pp. 2022–2031. The COLING 2016 Organizing Committee (2016). http://aclanthology.org/C16-1190
Ni, Z., Kong, F.: Enhancing long-distance dialogue history modeling for better dialogue ellipsis and coreference resolution. In: Wang, L., Feng, Y., Hong, Yu., He, R. (eds.) NLPCC 2021. LNCS (LNAI), vol. 13028, pp. 480–492. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88480-2_38
Pan, Z.F., Bai, K., Wang, Y., Zhou, L., Liu, X.: Improving open-domain dialogue systems via multi-turn incomplete utterance restoration. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, 3–7 November 2019, pp. 1824–1833. Association for Computational Linguistics (2019)
Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 6–12 July 2002, Philadelphia, PA, USA, pp. 311–318. ACL (2002)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, 25–29 October 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 1532–1543. ACL (2014)
Quan, J., Xiong, D., Webber, B., Hu, C.: GECOR: an end-to-end generative ellipsis and co-reference resolution model for task-oriented dialogue. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3–7, 2019, pp. 4546–4556. Association for Computational Linguistics (2019)
Quan, J., Zhang, S., Cao, Q., Li, Z., Xiong, D.: Risawoz: a large-scale multi-domain wizard-of-oz dataset with rich semantic annotations for task-oriented dialogue modeling. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16–20 November 2020, pp. 930–940. Association for Computational Linguistics (2020)
Ritter, A., Cherry, C., Dolan, W.B.: Data-driven response generation in social media. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Scotland, UK, July 2011, pp. 583–593. Association for Computational Linguistics (2011). http://aclanthology.org/D11-1054
Su, H., Shen, X., Zhang, R., Sun, F., Hu, P., Niu, C., Zhou, J.: Improving multi-turn dialogue modelling with utterance rewriter. In: Korhonen, A., Traum, D.R., Màrquez, L. (eds.) Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers. pp. 22–31. Association for Computational Linguistics (2019)
Xing, C., Wu, W.Y., Wu, Y., Zhou, M., Huang, Y., Ma, W.Y.: Hierarchical recurrent attention network for response generation. In: AAAI Conference on Artificial Intelligence (2017)
Zhang, X., Li, C., Yu, D., Davidson, S., Yu, Z.: Filling conversation ellipsis for better social dialog understanding. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, 7–12 February 2020, pp. 9587–9595. AAAI Press (2020)
Acknowledgments
This work was supported by the Projects 62276178 under the National Natural Science Foundation of China, the National Key RD Program of China under Grant No.2020AAA0108600 and the Priority Academic Program Development of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Q., Kong, F. (2023). Towards Better Dialogue Utterance Rewriting via a Gated Span-Copy Mechanism. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14262. Springer, Cham. https://doi.org/10.1007/978-3-031-44201-8_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-44201-8_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44200-1
Online ISBN: 978-3-031-44201-8
eBook Packages: Computer ScienceComputer Science (R0)