Mining Exploratory Queries for Conversational Search

What is it about?

Users’ queries are usually vague, and their search intents tend to be ambiguous, thereby needing search clarification to clarify users’ current 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 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 query. This paper focuses on mining exploratory queries as additional 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 constructed an evaluation dataset based on human annotations and conduct an extensive set of experiments. The results show that our proposed methods generate higher-quality exploratory queries compared with several baselines.

Featured Image

Why is it important?

We believe that mining these exploratory queries in the context of conversational search is important. First, as mentioned in existing studies [4, 10, 15, 25], users’ exploratory search behaviors are common in real-world search systems. Boldi et al. [4] reported that users’ exploratory search behaviors constituted 48-56% of a Yahoo! search log, even bigger than clarification behaviors (30-38%). Therefore, displaying an additional exploratory pane (yellow part in Figure 1) is a good extension of the existing search clarification in conversational search scenario. Second, these exploratory queries provide new topics or broader information space to users, which enhances the diversity of clickable options and improves the users’ search experience from new perspectives.