Summary-Oriented Question Generation for Informational Queries

TL;DR

This paper introduces a BERT-based model for generating summary-oriented questions that improve user understanding and interaction with QA systems, demonstrating state-of-the-art performance on the Natural Questions dataset and effective out-of-domain application.

Contribution

The paper presents a novel BERT-based Pointer-Generator Network for generating self-explanatory, summary-focused questions, achieving state-of-the-art results and effective cross-domain performance.

Findings

Achieved 20.1 BLEU-4 on NQ dataset for SQ generation.

Generated better questions for news articles compared to baseline.

Human evaluation confirms improved question quality.

Abstract

Users frequently ask simple factoid questions for question answering (QA) systems, attenuating the impact of myriad recent works that support more complex questions. Prompting users with automatically generated suggested questions (SQs) can improve user understanding of QA system capabilities and thus facilitate more effective use. We aim to produce self-explanatory questions that focus on main document topics and are answerable with variable length passages as appropriate. We satisfy these requirements by using a BERT-based Pointer-Generator Network trained on the Natural Questions (NQ) dataset. Our model shows SOTA performance of SQ generation on the NQ dataset (20.1 BLEU-4). We further apply our model on out-of-domain news articles, evaluating with a QA system due to the lack of gold questions and demonstrate that our model produces better SQs for news articles -- with further confirmation via a human evaluation.