Interactive query expansion for professional search applications

TL;DR

This paper explores interactive query expansion techniques tailored for professional search tasks, emphasizing the importance of linguistic cues and distributional language models to improve search effectiveness in complex, expert-driven scenarios.

Contribution

It introduces specialized query expansion methods that consider the structured nature of professional search strategies, enhancing search accuracy and efficiency.

Findings

Distributional language models improve query suggestions.

Linguistic cues like n-gram order optimize precision and recall.

Interactive expansion benefits complex professional search tasks.

Abstract

Knowledge workers (such as healthcare information professionals, patent agents and recruitment professionals) undertake work tasks where search forms a core part of their duties. In these instances, the search task is often complex and time-consuming and requires specialist expert knowledge to formulate accurate search strategies. Interactive features such as query expansion can play a key role in supporting these tasks. However, generating query suggestions within a professional search context requires that consideration be given to the specialist, structured nature of the search strategies they employ. In this paper, we investigate a variety of query expansion methods applied to a collection of Boolean search strategies used in a variety of real-world professional search tasks. The results demonstrate the utility of context-free distributional language models and the value of using linguistic cues such as ngram order to optimise the balance between precision and recall.