Mining Exploratory Queries for Conversational Search

Wenhan Liu, Ziliang Zhao, Yutao Zhu, Zhicheng Dou

Keywords: Conversational Search, Search Clarification, Exploratory Search

TL;DR: We focus on mining exploratory queries in conversational search which helps users explore more information they may also potentially interested in.

Abstract: Users' queries are usually vague, and their search intents tend to be ambiguous, thereby needing clarification. Search clarification has been proposed as an important technique to clarify users' current search intent by asking a clarifying question and providing several clickable sub-intent items as clarification options. However, in addition to drilling down the current query, users may also have exploratory needs that diverge from their current search intent. For example, a user searching for the query "Cartier women watches'' may also potentially want to explore some parallel information by issuing queries such as "Rolex women watches'' or "Cartier women bracelets'', named exploratory queries in this paper. These exploratory needs are common during the search process yet cannot be satisfied by current search clarification approaches which typically stick to the sub-intents of the current query. This paper focuses on mining exploratory queries as additional clickable options to meet users' exploratory needs in conversational search systems. Specifically, we first design a rule-based model that generates exploratory queries based on the current query's top retrieved documents. Then, we propose using the data generated by the rule-based model to train a neural generation model through multi-task learning for further generalization. Finally, we borrow the in-context learning ability of the large language model to generate exploratory queries based on prompt engineering. We conduct an extensive set of experiments and the results show that our proposed methods generate higher-quality exploratory queries compared with several baselines. The results also demonstrate that the structure information in top retrieved documents is useful for generating exploratory queries.

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: 636