Abstract
Conversational search faces incomplete and informal follow-up questions. Prior works address these by contextualizing user utterances with cues derived from the previous turns of the conversation. This approach works well when the conversation centers on prominent entities, for which knowledge bases (KBs) or language models (LMs) can provide rich background. This work addresses the unexplored direction where user questions are about tail entities, not featured in KBs and sparsely covered by LMs. We devise a new method, called CONSENT, for selectively contextualizing a user utterance with turns, KB-linkable entities, and mentions of tail and out-of-KB (OKB) entities. CONSENT derives relatedness weights from Sentence-BERT similarities and employs an integer linear program (ILP) for judiciously selecting the best context cues for a given set of candidate answers. This method couples the contextualization and answer-ranking stages, and jointly infers the best choices for both.
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
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
References
Adlakha, V., Dhuliawala, S., Suleman, K., de Vries, H., Reddy, S.: TopiOCQA: open-domain conversational question answering with topic switching (2021)
Aliannejadi, M., Kiseleva, J., Chuklin, A., Dalton, J., Burtsev, M.: Building and evaluating open-domain dialogue corpora with clarifying questions. In: EMNLP (2021)
Brown, T.B., et al.: Language models are few-shot learners. In: NIPS (2020)
Cao, Y., Xu, J., Liu, T.Y., Li, H., Huang, Y., Hon, H.W.: Adapting ranking SVM to document retrieval. In: SIGIR (2006)
Christmann, P., Roy, R.S., Weikum, G.: Conversational question answering on heterogeneous sources. In: SIGIR (2022)
Christmann, P., Saha Roy, R., Abujabal, A., Singh, J., Weikum, G.: Look before you hop: conversational question answering over knowledge graphs using judicious context expansion. In: CIKM (2019)
Christmann, P., Saha Roy, R., Weikum, G.: Conversational question answering on heterogeneous sources. In: SIGIR (2022)
Dalton, J., Xiong, C., Callan, J.: CAsT 2019: the conversational assistance track overview. In: Proceedings of the Twenty-Eighth Text REtrieval Conference (TREC 2019), Gaithersburg, Maryland (2019)
Dalton, J., Xiong, C., Callan, J.: Cast 2020: the conversational assistance track overview. In: TREC (2020)
Dalton, J., Xiong, C., Callan, J.: Cast 2021: the conversational assistance track overview. In: TREC (2021)
Elgohary, A., Peskov, D., Boyd-Graber, J.: Can you unpack that? Learning to rewrite questions-in-context. In: EMNLP-IJCNLP (2019)
Gao, J., Xiong, C., Bennett, P., Craswell, N.: Neural Approaches to Conversational Information Retrieval (2023)
Hai, N.L., Gerald, T., Formal, T., Nie, J.Y., Piwowarski, B., Soulier, L.: Cosplade: contextualizing splade for conversational information retrieval. In: Kamps, J., et al. (eds.) ECIR 2023. LNCS, vol. 13980, pp. 537–552. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-28244-7_34
Hoffart, J., Milchevski, D., Weikum, G.: STICS: searching with strings, things, and cats. In: SIGIR (2014)
Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: SIGIR (2020)
Kim, G., Kim, H., Park, J., Kang, J.: Learn to resolve conversational dependency: a consistency training framework for conversational question answering. In: ACL-IJCNLP (2021)
Krasakis, A.M., Yates, A., Kanoulas, E.: Zero-shot query contextualization for conversational search. In: SIGIR (2022)
Lin, J., Nogueira, R., Yates, A.: Pretrained transformers for text ranking: BERT and beyond. arXiv:2010.06467 (2020)
Lin, S., Yang, J., Lin, J.: Contextualized query embeddings for conversational search. In: EMNLP (2021)
Onoe, Y., Boratko, M., Durrett, G.: Modeling fine-grained entity types with box embeddings. In: ACL (2021)
OpenAI: GPT-4 technical report. arXiv:2303.08774 (2023)
Qu, C., et al.: Attentive history selection for conversational question answering. In: CIKM (2019)
Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: EMNLP (2019)
Robertson, S., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retrieval 3(4), 333–389 (2009)
Tredici, M.D., Barlacchi, G., Shen, X., Cheng, W., de Gispert, A.: Question rewriting for open-domain conversational QA: best practices and limitations. In: CIKM (2021)
Vakulenko, S., Longpre, S., Tu, Z., Anantha, R.: Question rewriting for end to end conversational question answering. In: WSDM (2021)
Vakulenko, S., Voskarides, N., Tu, Z., Longpre, S.: A comparison of question rewriting methods for conversational passage retrieval. In: ECIR (2021)
Voskarides, N., Li, D., Ren, P., Kanoulas, E., de Rijke, M.: Query resolution for conversational search with limited supervision. In: SIGIR (2020)
Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: ICLR (2021)
Yu, S., et al.: Few-shot generative conversational query rewriting. In: SIGIR (2020)
Yu, S., Liu, Z., Xiong, C., Feng, T., Liu, Z.: Few-shot conversational dense retrieval. In: SIGIR (2021)
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 Switzerland AG
About this paper
Cite this paper
Tran, H.D., Yates, A., Weikum, G. (2024). Conversational Search with Tail Entities. In: Goharian, N., et al. Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14609. Springer, Cham. https://doi.org/10.1007/978-3-031-56060-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-56060-6_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56059-0
Online ISBN: 978-3-031-56060-6
eBook Packages: Computer ScienceComputer Science (R0)