@inproceedings{shen-etal-2021-gtm,
    title = "{GTM}: A Generative Triple-wise Model for Conversational Question Generation",
    author = "Shen, Lei  and
      Meng, Fandong  and
      Zhang, Jinchao  and
      Feng, Yang  and
      Zhou, Jie",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.acl-long.271/",
    doi = "10.18653/v1/2021.acl-long.271",
    pages = "3495--3506",
    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 {\textquotedblleft}future{\textquotedblright} 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."
}