BriefGPT.xyz
May, 2016
一种分层潜变量编码器-解码器模型生成对话
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
HTML
PDF
Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau...
TL;DR
提出一种基于神经网络的生成架构，通过潜在的随机变量来建模具有复杂依赖关系的分层结构顺序数据，将该模型应用于对话响应生成任务并与最近的神经网络架构进行比较，实验证明该模型可以提高生成长输出的准确性并维持上下文信息。
Abstract
sequential data
often possesses a
hierarchical structure
with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process,
→