Generating Query Suggestions to Support Task-Based Search
This work addresses the challenge of supporting task-based search for users, but it appears incremental as it builds on existing probabilistic modeling and evaluation benchmarks.
The paper tackles the problem of generating query suggestions to help users complete their underlying search tasks by proposing a probabilistic modeling framework that extracts keyphrases from multiple sources and creates suggestions from them, evaluated using TREC Tasks track test suites.
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.