ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs

TL;DR

This paper introduces ISEEQ, a novel system that generates information-seeking questions from short user queries using knowledge graphs, retrieval, and reinforcement learning, significantly advancing conversational information seeking capabilities.

Contribution

ISEEQ is the first approach to generate high-quality ISQs from minimal input using knowledge graphs, retrieval, and deep reinforcement learning, outperforming existing baselines across multiple datasets.

Findings

ISEEQ outperforms baselines on five evaluation metrics.

It demonstrates strong transferability across different domains.

Human evaluation shows ISQ quality comparable to human questions.

Abstract

Conversational Information Seeking (CIS) is a relatively new research area within conversational AI that attempts to seek information from end-users in order to understand and satisfy users' needs. If realized, such a system has far-reaching benefits in the real world; for example, a CIS system can assist clinicians in pre-screening or triaging patients in healthcare. A key open sub-problem in CIS that remains unaddressed in the literature is generating Information Seeking Questions (ISQs) based on a short initial query from the end-user. To address this open problem, we propose Information SEEking Question generator (ISEEQ), a novel approach for generating ISQs from just a short user query, given a large text corpus relevant to the user query. Firstly, ISEEQ uses a knowledge graph to enrich the user query. Secondly, ISEEQ uses the knowledge-enriched query to retrieve relevant context passages to ask coherent ISQs adhering to a conceptual flow. Thirdly, ISEEQ introduces a new deep generative-adversarial reinforcement learning-based approach for generating ISQs. We show that ISEEQ can generate high-quality ISQs to promote the development of CIS agents. ISEEQ significantly outperforms comparable baselines on five ISQ evaluation metrics across four datasets having user queries from diverse domains. Further, we argue that ISEEQ is transferable across domains for generating ISQs, as it shows the acceptable performance when trained and tested on different pairs of domains. The qualitative human evaluation confirms ISEEQ-generated ISQs are comparable in quality to human-generated questions and outperform the best comparable baseline.