# Topic Propagation in Conversational Search

arXiv: https://arxiv.org/abs/2004.14054 · HTML: https://mlsanity.com/paper/2004.14054/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [MS MARCO: Benchmarking Ranking Models in the Large-Data Regime](https://mlsanity.com/paper/2105.04021/) (2021)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [A Comparison of Question Rewriting Methods for Conversational Passage Retrieval](https://mlsanity.com/paper/2101.07382/) (2021)
- [Query Performance Prediction: From Ad-hoc to Conversational Search](https://mlsanity.com/paper/2305.10923/) (2023)
- [Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval](https://mlsanity.com/paper/2405.12801/) (2024)
- [Human Emotion Verification by Action Languages via Answer Set Programming](https://mlsanity.com/paper/2601.12912/) (2026)
- [MICROS: Mixed-Initiative ConveRsatiOnal Systems Workshop](https://mlsanity.com/paper/2101.10219/) (2021)
- [CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite](https://mlsanity.com/paper/2403.11873/) (2024)
- [Rewriting Conversational Utterances with Instructed Large Language Models](https://mlsanity.com/paper/2410.07797/) (2024)

## Abstract (arXiv)

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.