GTM: A Generative Triple-Wise Model for Conversational Question Generation
arXiv:2106.03635
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.
To appear at ACL 2021 main conference (long paper)
References in corpus (5)
- Hierarchical Recurrent Attention Network for Response Generation
- Learning through Dialogue Interactions by Asking Questions
- Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection
- Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation
- Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network