Generating Query Suggestions to Support Task-Based Search

TL;DR

This paper presents a probabilistic framework for generating query suggestions that cover potential subtasks, aiding users in completing their underlying tasks during search.

Contribution

It introduces a novel probabilistic model that combines multiple sources of keyphrases to generate comprehensive query suggestions for task-based search.

Findings

Effective coverage of subtasks demonstrated on TREC Tasks datasets

Model components analyzed for contribution to suggestion quality

Improved query suggestion relevance shown in evaluations

Abstract

We address the problem of generating query suggestions to support users in completing their underlying tasks (which motivated them to search in the first place). Given an initial query, these query suggestions should provide a coverage of possible subtasks the user might be looking for. We propose a probabilistic modeling framework that obtains keyphrases from multiple sources and generates query suggestions from these keyphrases. Using the test suites of the TREC Tasks track, we evaluate and analyze each component of our model.