Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
Yiping Song,1 Rui Yan,2 Xiang Li,1 Dongyan Zhao,2 Ming Zhang1 1 School of EECS, Peking University, China 2 Institute of Computer Science and Technology, Peking University, China {songyiping, ruiyan, lixiang.eecs, zhaody, mzhang_cs
Abstract
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.
中文速览
开放域聊天机器人面临两难困境：基于检索的系统只能返回数据库中已有的回复，语义匹配也停留在词语表面；而基于循环神经网络（RNN）的生成式系统虽能造出新句子，却频繁输出"我不知道"这类毫无内容的万能回答。为此，研究者提出将两类方法融合：先用检索系统从海量语料中找到一条候选回复，再把原始问句和这条候选回复一起喂给双序列到序列模型（biseq2seq），让生成器在更丰富的信息引导下造出质量更高的新回复，最后用检索系统的打分器对检索结果和生成结果进行重排，取最优者作为最终答案。在中文开放域对话的主客观评测中，这一融合框架在多项指标上均大幅超越单独使用检索或生成的基线系统，证明了将两种路线取长补短的有效性，也为后续对话系统的集成设计提供了新思路。
原文 arXiv:1610.07149;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1610.07149v1