GTM: A Generative Triple-Wise Model for Conversational Question Generation

TL;DR

This paper introduces GTM, a hierarchical generative model for conversational question generation that improves question quality by modeling the triple (post-question-answer) as a unified structure with shared background and one-to-many relations.

Contribution

The paper proposes a novel hierarchical triple-wise generative model that captures the coherence and diversity of questions in open-domain conversations, addressing limitations of previous methods.

Findings

Significant improvement in question fluency, coherence, and diversity.

Outperforms baseline models on a large-scale CQG dataset.

Effective modeling of shared background and semantic mappings in triples.

Abstract

Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction. To avoid dull or deviated questions, some researchers tried to utilize answer, the "future" information, to guide question generation. However, they separate a post-question-answer (PQA) triple into two parts: post-question (PQ) and question-answer (QA) pairs, which may hurt the overall coherence. Besides, the QA relationship is modeled as a one-to-one mapping that is not reasonable in open-domain conversations. To tackle these problems, we propose a generative triple-wise model with hierarchical variations for open-domain conversational question generation (CQG). Latent variables in three hierarchies are used to represent the shared background of a triple and one-to-many semantic mappings in both PQ and QA pairs. Experimental results on a large-scale CQG dataset show that our method significantly improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.