IITD-DBAI: Multi-Stage Retrieval with Pseudo-Relevance Feedback and Query Reformulation

TL;DR

This paper presents a multi-stage retrieval approach using pseudo-relevance feedback and query reformulation to improve conversational search by maintaining context and key terms, achieving competitive results in CAsT-2021.

Contribution

It introduces a novel multi-stage retrieval method that combines classical IR techniques with pseudo-relevance feedback for conversational systems.

Findings

Achieved better than median NDCG@3 performance in CAsT-2021

Effectively preserved context and key terms across conversation turns

Demonstrated the effectiveness of classical IR methods in conversational retrieval

Abstract

Resolving the contextual dependency is one of the most challenging tasks in the Conversational system. Our submission to CAsT-2021 aimed to preserve the key terms and the context in all subsequent turns and use classical Information retrieval methods. It was aimed to pull as relevant documents as possible from the corpus. We have participated in automatic track and submitted two runs in the CAsT-2021. Our submission has produced a mean NDCG@3 performance better than the median model.