arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.05640cs.CLcs.AIcs.LG
收藏

排名增强对话生成

Ranking Enhanced Dialogue Generation

CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所网络数据科学与技术重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Alibaba Group(阿里巴巴集团)

Changying Hao, Liang Pang, Yanyan Lan, Fei Sun, Jiafeng Guo, Xueqi Cheng

摘要:

如何有效地利用对话历史是多轮对话生成中的一个关键问题。以前的工作通常采用各种神经网络架构(例如,递归神经网络、注意力机制和分层结构)来对历史进行建模。然而,Sankar等人最近的一项实证研究表明,这些架构缺乏理解和建模对话历史动态的能力。例如,广泛使用的体系结构对对话历史的扰动(诸如单词混洗、话语丢失和话语重新排序)不敏感。为了解决这个问题,我们在本文中提出了一个排名增强对话生成框架。尽管传统的表示编码器和响应生成模块,一个额外的排名模块被引入到模型之间的排名关系的前话语和连续的话语。具体来说,前一个话语和连续的话语被视为查询和相应的文档,并在学习过程中设计了局部和全局的排名损失。通过这种方式,可以明确地捕获对话历史中的动态。为了评估我们提出的模型,我们在三个公共数据集上进行了广泛的实验,即,bAbI、PersonaChat和JDC。实验结果表明,我们的模型产生更好的反应,在定量措施和人类的判断,与国家的最先进的对话生成模型。此外,我们给出了一些详细的实验分析,以显示改进来自哪里以及如何。

英文摘要:

How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation. Previous works usually employ various neural network architectures (e.g., recurrent neural networks, attention mechanisms, and hierarchical structures) to model the history. However, a recent empirical study by Sankar et al. has shown that these architectures lack the ability of understanding and modeling the dynamics of the dialogue history. For example, the widely used architectures are insensitive to perturbations of the dialogue history, such as words shuffling, utterances missing, and utterances reordering. To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper. Despite the traditional representation encoder and response generation modules, an additional ranking module is introduced to model the ranking relation between the former utterance and consecutive utterances. Specifically, the former utterance and consecutive utterances are treated as query and corresponding documents, and both local and global ranking losses are designed in the learning process. In this way, the dynamics in the dialogue history can be explicitly captured. To evaluate our proposed models, we conduct extensive experiments on three public datasets, i.e., bAbI, PersonaChat, and JDC. Experimental results show that our models produce better responses in terms of both quantitative measures and human judgments, as compared with the state-of-the-art dialogue generation models. Furthermore, we give some detailed experimental analysis to show where and how the improvements come from.

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。

↑