BriefGPT.xyz
Jul, 2019
对话中有效地将发言者信息纳入话语编码
Effective Incorporation of Speaker Information in Utterance Encoding in Dialog
HTML
PDF
Tianyu Zhao, Tatsuya Kawahara
TL;DR
本文介绍了一种相对话者建模的方法，用于解决在对话中标记说话人时可能出现的一致性问题。实验结果显示，该方法在对话行为识别和响应生成方面表现更为出色和一致。
Abstract
In
dialog studies
, we often encode a dialog using a
hierarchical encoder
where each utterance is converted into an utterance vector, and then a sequence of utterance vectors is converted into a dialog vector. Sin
→