IITD-DBAI: Multi-Stage Retrieval with Pseudo-Relevance Feedback and Query Reformulation
This work addresses the problem of maintaining context in conversational search for users, but it is incremental as it builds on classical IR methods.
The paper tackled the challenge of contextual dependency in conversational systems by using multi-stage retrieval with pseudo-relevance feedback and query reformulation, achieving a mean NDCG@3 performance better than the median model in the CAsT-2021 benchmark.
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.