Generating Multi-turn Clarification for Web Information Seeking

Ziliang Zhao, Zhicheng Dou

Keywords: Search Clarification, Conversational Search, Information Retrieval

TL;DR: In this paper, we make the first attempt to extend the multi-turn clarification generation to the Web search for clarifying users' ambiguous or faceted intents.

Abstract: Asking multi-turn clarifying questions has been applied in various conversational search systems to help recommend people, commodities, and images to users. However, its importance is still not emphasized in Web search. In this paper, we make the first attempt to extend the multi-turn clarification generation to Web search for clarifying users' ambiguous or faceted intents. Compared with other conversational search scenarios, Web search queries are more complicated, so the clarification should be generated instead of selected that is commonly applied in existing studies. To this end, we first define the whole process of multi-turn Web search clarification composed of clarification candidate generation, optimal clarification selection, and document retrieval. Due to the lack of multi-turn open-domain clarification data, we first design a simple yet effective rule-based method to fit the above three components. After that, by utilizing the in-context learning and zero-shot instruction ability of large language models (LLMs), we implement clarification generation and selection by prompting LLMs with a few demonstrations and declarations, further improving the clarification effectiveness. To evaluate our proposed methods, we first apply the Qulac dataset to measure whether our methods can improve the ability to retrieve documents. We further evaluate the quality of generated aspect items with MIMICS dataset. Experimental results show that, compared with existing single-turn methods for Web search clarification, our proposed framework is more suitable for open-domain Web search systems in asking multi-turn clarification questions to clarify users' ambiguous or faceted intents.

Track: Search

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 2493