2020
Conference article  Open Access

Topic propagation in conversational search

Mele I., Muntean C. I., Nardini F. M., Perego R., Tonellotto N., Frieder O.

Information Retrieval (cs.IR)  Computation and Language (cs.CL)  Computer Science - Information Retrieval  FOS: Computer and information sciences  Conversational IR  Query rewriting  Passage ranking  Computer Science - Computation and Language 

In a conversational context, a user expresses her multi-faceted information need as a sequence of natural-language questions, i.e., utterances. Starting from a given topic, the conversation evolves through user utterances and system replies. The retrieval of documents relevant to a given utterance in a conversation is challenging due to ambiguity of natural language and to the difficulty of detecting possible topic shifts and semantic relationships among utterances. We adopt the 2019 TREC Conversational Assistant Track (CAsT) framework to experiment with a modular architecture performing: (i) topic-aware utterance rewriting, (ii) retrieval of candidate passages for the rewritten utterances, and (iii) neural-based re-ranking of candidate passages. We present a comprehensive experimental evaluation of the architecture assessed in terms of traditional IR metrics at small cutoffs. Experimental results show the effectiveness of our techniques that achieve an improvement of up to $0.28$ (+93%) for P@1 and $0.19$ (+89.9%) for nDCG@3 w.r.t. the CAsT baseline.

Source: SIGIR 2020 - 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2057–2060, Online Conference, July 25-30, 2020


[1] M. Aliannejadi, M. Chakraborty, E. A. Ríssola, and F. Crestani. 2020. Harnessing Evolution of Multi-Turn Conversations for Efective Answer Retrieval. In CHIIR.
[2] H. Cao, D. Jiang, J. Pei, Q. He, Z. Liao, E. Chen, and H. Li. 2008. Context-Aware Query Suggestion by Mining Click-through and Session Data. In SIGKDD. ACM.
[3] C. L. A. Clark, S. Büttcher, and G. V. Cormack. 2010. Information Retrieval: Implementing and Evaluating Search Engines. MIT Press.
[4] M. Gardner, J. Grus, M. Neumann, O. Tafjord, P. Dasigi, N. F. Liu, M. Peters, M. Schmitz, and L. S. Zettlemoyer. 2017. AllenNLP: A Deep Semantic Natural Language Processing Platform. arXiv:1803.07640 (2017).
[5] S. Hofstätter, N. Rekabsaz, C. Eickhof, and A. Hanbury. 2019. On the Efect of Low-Frequency Terms on Neural-IR Models. arXiv:1904.1268 (2019).
[6] K. Lee, L. He, M. Lewis, and L. Zettlemoyer. 2017. End-to-end Neural Coreference Resolution. arXiv:1707.07045 (2017).
[7] R. Nogueira and K. Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085 (2019).
[8] G. Ren, X. Ni, M. Malik, and Q. Ke. 2018. Conversational Query Understanding Using Sequence to Sequence Modeling. In WWW. 1715 - 1724.
[9] L. Yang, M. Qiu, C. Qu, J. Guo, Y. Zhang, W. B. Croft, J. Huang, and H. Chen. 2018. Response Ranking with Deep Matching Networks and External Knowledge in Information-Seeking Conversation Systems. In SIGIR. ACM, 245 - 254.
[10] L. Yang, H. Zamani, Y. Zhang, J. Guo, and W. B. Croft. 2017. Neural matching models for question retrieval and next question prediction in conversation. arXiv:1707.05409 (2017).

Metrics



Back to previous page
BibTeX entry
@inproceedings{oai:it.cnr:prodotti:434450,
	title = {Topic propagation in conversational search},
	author = {Mele I. and Muntean C. I. and Nardini F. M. and Perego R. and Tonellotto N. and Frieder O.},
	doi = {10.1145/3397271.3401268 and 10.48550/arxiv.2004.14054},
	booktitle = {SIGIR 2020 - 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2057–2060, Online Conference, July 25-30, 2020},
	year = {2020}
}

BigDataGrapes
Big Data to Enable Global Disruption of the Grapevine-powered Industries


OpenAIRE