Interactive Query Clarification and Refinement via User Simulation

TL;DR

This paper introduces a fully simulated framework for multi-turn query clarification in information retrieval, enabling systems to interact with user agents to better understand ambiguous queries and improve document ranking.

Contribution

It presents a novel simulation-based approach for multi-turn query clarification, surpassing previous limited or log-based interaction methods.

Findings

Effective multi-turn clarification improves retrieval accuracy

Simulation framework enables scalable testing of clarification strategies

Outperforms existing single-interaction approaches

Abstract

When users initiate search sessions, their queries are often unclear or might lack of context; this resulting in inefficient document ranking. Multiple approaches have been proposed by the Information Retrieval community to add context and retrieve documents aligned with users' intents. While some work focus on query disambiguation using users' browsing history, a recent line of work proposes to interact with users by asking clarification questions or/and proposing clarification panels. However, these approaches count either a limited number (i.e., 1) of interactions with user or log-based interactions. In this paper, we propose and evaluate a fully simulated query clarification framework allowing multi-turn interactions between IR systems and user agents.