期刊
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
卷 23, 期 3, 页码 1989-2002出版社
SPRINGER
DOI: 10.1007/s11280-019-00688-8
关键词
Dialogue model; Hierarchical encoder-decoder; Log-likelihood optimization; Dialogue intention
We propose an end-to-end dialogue model based on a hierarchical encoder-decoder, which employed a discrete latent variable to learn underlying dialogue intentions. The system is able to model the structure of utterances dominated by statistics of the language and the dependencies among utterances in dialogues without manual dialogue state design. We argue that the latent discrete variable interprets the intentions that guide machine responses generation. We also propose a model which can be refined autonomously with reinforcement learning, due to that intention selection at each dialogue turn can be formulated as a sequential decision-making process. Our experiments show that exact MLE optimized model is much more robust than neural variational inference on dialogue success rate with limited BLEU sacrifice.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据