Abstract
Conversational Search (CS) aims to retrieve relevant passages from multiple documents based on the questions given by the user in conversations. Since users ask questions and get answers step by step through multiple rounds of conversations, conversation history is usually utilized to enhance retrieval accuracy. Existing methods rely too heavily on conversation history to retrieve while ignoring the semantics of the current question. However, the conversation history is not fully relevant to the current question, which includes some document information irrelevant to the current question. It is challenging to extract utterances information relevant to the current question from the conversation history to facilitate retrieval without breaking semantic coherence. We propose the reranker based on the Utterance-Mask-Passage (UtMP) post-training method to address this challenge, which includes three training tasks: passage relevance classification, utterance correlation classification, and context mask. Our method decomposes complex conversation history into short contexts, learns fine-grained semantic associations between utterances and document passages through three training tasks based on multi-task learning, and further learns correlations between conversation history and document passages based on contrastive learning. On the MultiDoc2Dial dataset, our results are 1.1% and 1.2% higher than the SOTA on the Recall@1 and MRR@10 metrics, respectively, which verifies the improvement of our method on retrieval performance. Extensive experiments show that our method helps deal with conversation histories with multiple documents information.
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
Bansal, S., et al.: R3: refined retriever-reader pipeline for multidoc2dial. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 148–154 (2022)
Burges, C.J.: From Ranknet to Lambdarank to Lambdamart: an overview. Learning 11(23–581), 81 (2010)
Chen, W., et al.: Contextual fine-to-coarse distillation for coarse-grained response selection in open-domain conversations. arXiv preprint arXiv:2109.13087 (2021)
Du, M., et al.: Topic-grained text representation-based model for document retrieval. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. LNCS, vol. 13531. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-15934-3_64
Feng, S., Patel, S.S., Wan, H., Joshi, S.: MultiDoc2Dial: modeling dialogues grounded in multiple documents. arXiv preprint arXiv:2109.12595 (2021)
Han, J., Hong, T., Kim, B., Ko, Y., Seo, J.: Fine-grained post-training for improving retrieval-based dialogue systems. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1549–1558 (2021)
Jang, Y., et al.: Improving multiple documents grounded goal-oriented dialog systems via diverse knowledge enhanced pretrained language model. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 136–141 (2022)
Jeffrey, D., Chenyan, X., Jamie, C.: CAsT 2019: the conversational assistance track overview. In: TREC (2019)
Jiang, Y., Hadifar, A., Deleu, J., Demeester, T., Develder, C.: UGent-T2K at the 2nd DialDoc shared task: a retrieval-focused dialog system grounded in multiple documents. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 115–122 (2022)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)
Li, J., et al.: Dialogue history matters! personalized response selection in multi-turn retrieval-based chatbots. ACM Trans. Inf. Syst. (TOIS) 39(4), 1–25 (2021)
Li, K., et al.: Grounded dialogue generation with cross-encoding re-ranker, grounding span prediction, and passage dropout. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 123–129 (2022)
Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1871–1880 (2019)
Tran, N., Litman, D.: Getting better dialogue context for knowledge identification by leveraging document-level topic shift. In: Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 368–375 (2022)
Whang, T., et al.: Do response selection models really know what’s next? Utterance manipulation strategies for multi-turn response selection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 14041–14049 (2021)
Zhang, S., Du, Y., Liu, G., Yan, Z., Cao, Y.: G4: grounding-guided goal-oriented dialogues generation with multiple documents. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 108–114 (2022)
Zhou, X., et al.: Multi-turn response selection for chatbots with deep attention matching network. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1118–1127 (2018)
Zhu, F., Lei, W., Wang, C., Zheng, J., Poria, S., Chua, T.S.: Retrieving and reading: a comprehensive survey on open-domain question answering. arXiv preprint arXiv:2101.00774 (2021)
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 Singapore Pte Ltd.
About this paper
Cite this paper
He, S., Zhang, S., Zhang, X., Feng, Z. (2023). Conversational Search Based on Utterance-Mask-Passage Post-training. In: Wang, H., Han, X., Liu, M., Cheng, G., Liu, Y., Zhang, N. (eds) Knowledge Graph and Semantic Computing: Knowledge Graph Empowers Artificial General Intelligence. CCKS 2023. Communications in Computer and Information Science, vol 1923. Springer, Singapore. https://doi.org/10.1007/978-981-99-7224-1_12
Download citation
DOI: https://doi.org/10.1007/978-981-99-7224-1_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7223-4
Online ISBN: 978-981-99-7224-1
eBook Packages: Computer ScienceComputer Science (R0)