Abstract
Multi-turn dialogue response generation aims to generate a response with consideration of the context. It is not equal to multiple single-turn dialogues due to the context dependence of response. Many existing models achieve great success for response generation, but they still struggle to model the contextual semantics of dialogue history. Sequence models have difficulties to explore the interactive relations between contextual utterances, which affects the coherence of generated responses. To solve the issue, we propose a discourse relation-aware model, which encodes the contextual utterances with a directed acyclic graph neural network (DAGNN) with constraints on dialogue-specific discourse relations to better model the intrinsic structure. Besides, we introduce an auxiliary discourse relation recognition task to enhance the model’s ability of representing the context. Extensive experimental results show that our proposed model outperforms baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asher, N., Hunter, J., Morey, M., Benamara, F., Afantenos, S.: Discourse structure and dialogue acts in multiparty dialogue: the stac corpus. In: Proceedings of the 10th LREC, pp. 2721–2727 (2016)
Chen, W., et al.: Dialogved: a pre-trained latent variable encoder-decoder model for dialog response generation. In: Proceedings of the 60th ACL, pp. 4852–4864 (2022)
Feng, X., Feng, X., Qin, B., Geng, X.: Dialogue discourse-aware graph model and data augmentation for meeting summarization. In: Proceedings of the IJCAI, pp. 3808–3814 (2021)
Gu, X., Yoo, K.M., Ha, J.W.: Dialogbert: discourse-aware response generation via learning to recover and rank utterances. In: Proceedings of the AAAI, pp. 12911–12919 (2021)
Gubelmann, R., Handschuh, S.: Context matters: a pragmatic study of plms’ negation understanding. In: Proceedings of the 60th ACL, pp. 4602–4621 (2022)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th ACL, pp. 7871–7880 (2020)
Li, J., Liu, M., Kan, M.Y., Zheng, Z., Wang, Z., et al.: Molweni: a challenge multiparty dialogues-based machine reading comprehension dataset with discourse structure. In: Proceedings of the 28th COLING, pp. 2642–2652 (2020)
Li, J., et al.: Dadgraph: a discourse-aware dialogue graph neural network for multiparty dialogue machine reading comprehension. In: Proceedings of the 2021 IJCNN, pp. 1–8 (2021)
Li, J., Galley, M., Brockett, C., Gao, J., Dolan, W.B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 NAACL: Human Language Technologies, pp. 110–119 (2016)
Li, Y., Zhao, H.: Self-and pseudo-self-supervised prediction of speaker and key-utterance for multi-party dialogue reading comprehension. In: Findings of the 2021 EMNLP, pp. 2053–2063 (2021)
Lowe, R., Pow, N., Serban, I.V., Pineau, J.: The ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. In: Proceedings of the 16th SIGDIAL, pp. 285–294 (2015)
Ma, M.D., Bowden, K., Wu, J., et al.: Implicit discourse relation identification for open-domain dialogues. In: Proceedings of the 57th ACL, pp. 666–672 (2019)
Papineni, K., Roukos, S., Ward, T., et al.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th ACL, pp. 311–318 (2002)
Prasad, R., et al.: The penn discourse treebank 2.0. In: Proceedings of the 6th LREC (2008)
Qi, W., et al.: Prophetnet: predicting future n-gram for sequence-to-sequencepre-training. In: Findings of the 2020 EMNLP, pp. 2401–2410 (2020)
Radford, A., et al.: Language models are unsupervised multitask learners. In: OpenAI blog, p. 9 (2019)
Roller, S., et al.: Recipes for building an open-domain chatbot. In: Proceedings of the EACL (2021)
Serban, I., Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the AAAI, pp. 3776–3783 (2016)
Serban, I., et al.: A hierarchical latent variable encoder-decoder model for generating dialogues. In: Proceedings of the AAAI, pp. 3295–3301 (2017)
Shang, L., Lu, Z., Li, H.: Neural responding machine for short-text conversation. In: Proceedings of the 53rd ACL and the 7th IJCNLP, pp. 1577–1586 (2015)
Shao, Y., Gouws, S., Britz, D., Goldie, A., Strope, B., Kurzweil, R.: Generating high-quality and informative conversation responses with sequence-to-sequence models. In: Proceedings of the 2017 EMNLP, pp. 2210–2219 (2017)
Shen, L., Feng, Y., Zhan, H.: Modeling semantic relationship in multi-turn conversations with hierarchical latent variables. In: Proceedings of the 57th ACL, pp. 5497–5502 (2019)
Shen, W., Wu, S., Yang, Y., Quan, X.: Directed acyclic graph network for conversational emotion recognition. In: Proceedings of the 59th ACL and the 11th IJCNLP, pp. 1551–1560 (2021)
Shi, Z., Huang, M.: A deep sequential model for discourse parsing on multi-party dialogues. In: Proceedings of the AAAI, pp. 7007–7014 (2019)
Stone, M., Stojnic, U., Lepore, E.: Situated utterances and discourse relations. In: Proceedings of the 10th IWCS, pp. 390–396 (2013)
Sun, Y., Yu, N., Fu, G.: A discourse-aware graph neural network for emotion recognition in multi-party conversation. In: Findings of the 2021 EMNLP, pp. 2949–2958 (2021)
Sutskever, I., et al.: Sequence to sequence learning with neural networks. In: Proceedings of the NeurIPS, vol. 195, pp. 496–527 (2014)
Thost, V., Chen, J.: Directed acyclic graph neural networks. In: Proceedings of the ICLR (2021)
Tonelli, S., Riccardi, G., Prasad, R., Joshi, A.: Annotation of discourse relations for conversational spoken dialogs. In: Proceedings of the 7th LREC (2010)
Zhang, H., Lan, Y., Pang, L., Chen, H., et al.: Modeling topical relevance for multi-turn dialogue generation. In: Proceedings of the IJCAI, pp. 3737–3743 (2020)
Zhang, H., Lan, Y., Pang, L., Guo, J., Cheng, X.: Recosa: Detecting the relevant contexts with self-attention for multi-turn dialogue generation. In: Proceedings of the 57th ACL, pp. 3721–3730 (2019)
Zhang, S., Dinan, E., Urbanek, J., et al.: Personalizing dialogue agents: I have a dog, do you have pets too? In: Proceedings of the 56th ACL, pp. 2204–2213 (2018)
Zhang, W., et al.: A static and dynamic attention framework for multi turn dialogue generation. In: JACM, vol. 41 (2022)
Zhang, Y., et al.: Dialogpt: large-scale generative pre-training for conversational response generation. In: Proceedings of the 58th ACL: System Demonstrations, pp. 270–278 (2020)
Acknowledgement
Our work is supported by the National Natural Science Foundation of China under Grant (61976154).
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
Wang, H., He, R., Jia, Y., Xu, J., Wang, B. (2023). Discourse Relation-Aware Multi-turn Dialogue Response Generation. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14302. Springer, Cham. https://doi.org/10.1007/978-3-031-44693-1_66
Download citation
DOI: https://doi.org/10.1007/978-3-031-44693-1_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44692-4
Online ISBN: 978-3-031-44693-1
eBook Packages: Computer ScienceComputer Science (R0)