Interactive Information Need Prediction with Intent and Context

TL;DR

This paper explores an interactive framework for predicting user information needs by combining user-selected context and partial intent, utilizing generative and retrieval models to improve accuracy and applicability.

Contribution

It introduces a novel interactive approach that leverages user input and language models for more accurate information need prediction.

Findings

Prediction is feasible in many cases.

Partial intent improves prediction with large contexts.

Framework is promising for real-world use.

Abstract

The ability to predict a user's information need would have wide-ranging implications, from saving time and effort to mitigating vocabulary gaps. We study how to interactively predict a user's information need by letting them select a pre-search context (e.g., a paragraph, sentence, or singe word) and specify an optional partial search intent (e.g., "how", "why", "applications", etc.). We examine how various generative language models can explicitly make this prediction by generating a question as well as how retrieval models can implicitly make this prediction by retrieving an answer. We find that this prediction process is possible in many cases and that user-provided partial search intent can help mitigate large pre-search contexts. We conclude that this framework is promising and suitable for real-world applications.