# Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval

arXiv: https://arxiv.org/abs/2102.08795 · HTML: https://mlsanity.com/paper/2102.08795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 17 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension](https://mlsanity.com/paper/1910.09753/) (2019)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Query Resolution for Conversational Search with Limited Supervision](https://mlsanity.com/paper/2005.11723/) (2020)
- [A Comparison of Question Rewriting Methods for Conversational Passage Retrieval](https://mlsanity.com/paper/2101.07382/) (2021)
- [A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering](https://mlsanity.com/paper/2010.06835/) (2020)

## Abstract (arXiv)

This paper describes the participation of UvA.ILPS group at the TREC CAsT 2020 track. Our passage retrieval pipeline consists of (i) an initial retrieval module that uses BM25, and (ii) a re-ranking module that combines the score of a BERT ranking model with the score of a machine comprehension model adjusted for passage retrieval. An important challenge in conversational passage retrieval is that queries are often under-specified. Thus, we perform query resolution, that is, add missing context from the conversation history to the current turn query using QuReTeC, a term classification query resolution model. We show that our best automatic and manual runs outperform the corresponding median runs by a large margin.