《计算机应用研究》|Application Research of Computers

基于多视角对抗学习的开放域对话生成模型

Open domain dialogue generation model based on multi-view adversarial learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张凉,杨燕,陈成才,贺樑
机构 1.华东师范大学 计算机科学与技术学院,上海 200062;2.上海智臻智能网络科技股份有限公司 小i机器人研究院,上海 201803
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)02-008-0372-05
DOI 10.19734/j.issn.1001-3695.2020.01.0011
摘要 近年来,随着智能家居的普及,对话系统在生活中发挥着越来越重要的作用,基于神经网络构建的生成式对话系统由于其灵活性高受到了许多研究者的关注。以提高生成模型对话的流畅性、上下文相关性为目的,提出基于多视角对抗学习的开放域对话生成模型。其中,模型生成器是基于检索到的相似对话进行改写得到生成的对话;模型的判别器是由两个二分类器共同组成的,该二元判别器分别从句子、对话两个层面多视角地对生成句子进行判别。在中文对话语料上进行实验,该模型在人工评价和自动评测上的得分都高于目前常用的对话生成模型。实验结果表明,利用二元判别器多视角训练可以同时提高生成回复的流畅度和上下文相关性。
关键词 对话生成; 对话系统; 对抗学习; 改写模型
基金项目 上海市教科委重点项目(18511105502)
本文URL http://www.arocmag.com/article/01-2021-02-008.html
英文标题 Open domain dialogue generation model based on multi-view adversarial learning
作者英文名 Zhang Liang, Yang Yan, Chen Chengcai, He Liang
机构英文名 1.School of Computer Science & Technology,East China Normal University,Shanghai 200062,China;2.Shanghai Xiao'i Robot Technology Co. Ltd,Shanghai 201803,China
英文摘要 Recently, with the emergence and popularity of intelligent applications, non-task oriented dialogue system has played an increasingly important role in daily life. Generation-based dialogue systems receive extraordinary attention of some researchers because they are more flexible. In order to improve the fluency and contextual relevance of the responses generated by models, this paper proposed an open domain dialogue generation model based on binary discriminator in terms of a multi-view adversarial learning framework. The generator of the model rewrote a retrieved response to get a generated response. While the discriminator was composed of two binary classifiers and distinguished the human-generated responses from machine-generated ones. Experiments on a Chinese dialogue corpus show that the model has higher scores on both human and automatic evaluation than baselines. Experiments also show that multi-view training with binary discriminators can improve both the fluency and contextual relevance of the generated responses.
英文关键词 dialogue generation; dialogue system; adversarial learning; revise model
参考文献 查看稿件参考文献
 
收稿日期 2020/1/21
修回日期 2020/3/15
页码 372-376
中图分类号 TP391.1
文献标志码 A