Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrieval

TL;DR

This paper presents a deep learning approach for selecting clarification questions in conversational search, improving user-system interaction by leveraging passage retrieval in both open domain and customer-support scenarios.

Contribution

It introduces a passage retrieval-based fine-tuning method for ranking clarification questions, advancing mixed-initiative conversational search capabilities.

Findings

Effective in open domain web search

Performs well in customer-support scenarios

Enhances clarification question relevance

Abstract

We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user response, in order to clarify her information needs. We focus on the task of selecting the next clarification question, given the conversation context. Our method leverages passage retrieval from a background content to fine-tune two deep-learning models for ranking candidate clarification questions. We evaluated our method on two different use-cases. The first is an open domain conversational search in a large web collection. The second is a task-oriented customer-support setup. We show that our method performs well on both use-cases.