Zero-shot Query Contextualization for Conversational Search

TL;DR

This paper introduces a zero-shot method for conversational search that adapts a pre-trained dense retriever to contextualize user questions without additional training, effectively improving retrieval performance.

Contribution

It presents a novel zero-shot approach that leverages pre-trained models for conversational search, eliminating the need for large-scale conversational datasets.

Findings

Effective retrieval performance demonstrated

Contextualization biases towards salient conversation terms

Insights into latent space contextualization

Abstract

Current conversational passage retrieval systems cast conversational search into ad-hoc search by using an intermediate query resolution step that places the user's question in context of the conversation. While the proposed methods have proven effective, they still assume the availability of large-scale question resolution and conversational search datasets. To waive the dependency on the availability of such data, we adapt a pre-trained token-level dense retriever on ad-hoc search data to perform conversational search with no additional fine-tuning. The proposed method allows to contextualize the user question within the conversation history, but restrict the matching only between question and potential answer. Our experiments demonstrate the effectiveness of the proposed approach. We also perform an analysis that provides insights of how contextualization works in the latent space, in essence introducing a bias towards salient terms from the conversation.