GTM:一个生成式三重会话问题生成模型
GTM: A Generative Triple-Wise Model for Conversational Question Generation
摘要:
在开放域会话中生成一些吸引人的问题是改善人机交互并将话题引向更广或更深方向的有效方法。为了避免问题的枯燥或偏离,一些研究者试图利用答案这一“未来”信息来指导问题的生成。然而,他们将后问题-答案(PQA)三元组分成两部分:后问题(PQ)和问题-答案(QA)对,这可能会损害整体的连贯性。此外,问答关系被建模为一对一的映射,这在开放域会话中是不合理的。为了解决这些问题,我们提出了一个生成的三重模型与层次变化的开放域会话问题生成(CQG)。三个层次中的潜变量用于表示PQ和QA对中的三元组和一对多语义映射的共享背景。在大规模CQG数据集上的实验结果表明,我们的方法在流畅性,一致性和多样性方面显着提高了问题的质量。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。