Topic Propagation in Conversational Search
This work addresses the problem of ambiguous and shifting topics in conversational search for users and systems, representing an incremental improvement over existing methods.
The paper tackles the challenge of retrieving relevant documents for utterances in conversational search by proposing a modular architecture that includes topic-aware utterance rewriting, passage retrieval, and neural re-ranking, achieving improvements of up to 0.28 (+93%) for P@1 and 0.19 (+89.9%) for nDCG@3 compared to the baseline.
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 up to 0.28 (+93%) for P@1 and 0.19 (+89.9%) for nDCG@3 w.r.t. the CAsT baseline.