arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1610.07149cs.CL
收藏

两个总比一个好:一个基于检索和生成的对话系统

Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

Peking University(北京大学)

Yiping Song, Rui Yan, Xiang Li, Dongyan Zhao, Ming Zhang

摘要:

开放域人机对话是自然语言处理领域的一个研究热点。与基于规则或模板的特定领域对话系统相反,开放领域对话通常需要数据驱动的方法,这些方法可以大致分为两类:基于检索的系统和基于生成的系统。检索系统在大型数据库中搜索用户发出的话语(称为查询),并返回与查询最匹配的回复。生成方法,通常基于递归神经网络(RNN),可以合成新的回复,但它们存在生成简短,无意义的话语的问题。在本文中,我们提出了一种新的合奏检索为基础的和生成为基础的对话系统在开放领域。在我们的方法中,除了原始查询之外,检索到的候选项还被馈送到基于RNN的回复生成器,以便神经模型能够了解更多信息。然后,将生成的回复作为新的候选者反馈以进行后重新排序。实验结果表明,这样的集成优于它的每一个单独的部分,由一个大的利润。

英文摘要:

Open-domain human-computer conversation has attracted much attention in the field of NLP. Contrary to rule- or template-based domain-specific dialog systems, open-domain conversation usually requires data-driven approaches, which can be roughly divided into two categories: retrieval-based and generation-based systems. Retrieval systems search a user-issued utterance (called a query) in a large database, and return a reply that best matches the query. Generative approaches, typically based on recurrent neural networks (RNNs), can synthesize new replies, but they suffer from the problem of generating short, meaningless utterances. In this paper, we propose a novel ensemble of retrieval-based and generation-based dialog systems in the open domain. In our approach, the retrieved candidate, in addition to the original query, is fed to an RNN-based reply generator, so that the neural model is aware of more information. The generated reply is then fed back as a new candidate for post-reranking. Experimental results show that such ensemble outperforms each single part of it by a large margin.

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。

↑