Abstract
Conversational Search (CS) aims to satisfy complex information needs via multi-turn user-agent interactions. During this process, multiple documents need to be retrieved based on the conversation history to respond to the user. However, existing approaches still make it difficult to distinguish irrelevant information from the user’s question at the semantic level. When a conversation involves multiple documents, it sometimes affects the retrieval performance negatively. In order to enhance the model’s ability to comprehend conversations and distinguish passages in irrelevant documents via multi-document information, we propose an unsupervised multi-document conversation segmentation method and a zero-shot Large Language Model (LLM)-based document summarization method to extract multi-document information from conversation history and documents respectively for amending the lack of training data for extracting multiple document information. We further present the Passage-Segment-Document (PSD) post-training method to train the reranker using the extracted multi-document information in combination with a multi-task learning method. The results on the MultiDoc2Dial dataset verifies the improvement of our method on retrieval performance. Extensive experiments show the strong performance of our method for dealing with conversation histories that contain multi-document information.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
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, DialDoc@ACL 2022, Dublin, Ireland, May 26, 2022, pp. 148–154 (2022)
Bonifacio, L., Abonizio, H., Fadaee, M., Nogueira, R.: Inpars: data augmentation for information retrieval using large language models (2022)
Feng, S., Patel, S.S., Wan, H., Joshi, S.: Multidoc2dial: modeling dialogues grounded in multiple documents, pp. 6162–6176 (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)
He, S., Zhang, S., Zhang, X., Feng, Z.: Conversational search based on utterance-mask-passage post-training. In: China Conference on Knowledge Graph and Semantic Computing (2023)
Ishii, E., Xu, Y., Cahyawijaya, S., Wilie, B.: Can question rewriting help conversational question answering? pp. 94–99 (2022)
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)
Jeronymo, V., et al.: Inpars-v2: large language models as efficient dataset generators for information retrieval. arXiv preprint arXiv:2301.01820 (2023)
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, pp. 6769–6781 (2020)
Kim, S., Kim, G.: Saving dense retriever from shortcut dependency in conversational search, pp. 10278–10287 (2022)
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)
Mao, K., et al.: Learning denoised and interpretable session representation for conversational search. In: Proceedings of the ACM Web Conference, pp. 3193–3202 (2023)
Shen, T., Long, G., Geng, X., Tao, C., Zhou, T., Jiang, D.: Large language models are strong zero-shot retriever. arXiv preprint arXiv:2304.14233 (2023)
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)
Wang, Z., Tu, Y., Rosset, C., Craswell, N., Wu, M., Ai, Q.: Zero-shot clarifying question generation for conversational search. In: Proceedings of the ACM Web Conference 2023, pp. 3288–3298 (2023)
Wu, Z., et al.: CONQRR: conversational query rewriting for retrieval with reinforcement learning. arXiv preprint arXiv:2112.08558 (2021)
Xu, Y., Zhao, H., Zhang, Z.: Topic-aware multi-turn dialogue modeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 14176–14184 (2021)
Yu, W., et al.: Generate rather than retrieve: large language models are strong context generators. arXiv preprint arXiv:2209.10063 (2022)
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)
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., Hashimoto, T.B.: Benchmarking large language models for news summarization. arXiv preprint arXiv:2301.13848 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 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. (2024). Improve Conversational Search with Multi-document Information. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1967. Springer, Singapore. https://doi.org/10.1007/978-981-99-8178-6_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-8178-6_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8177-9
Online ISBN: 978-981-99-8178-6
eBook Packages: Computer ScienceComputer Science (R0)