BriefGPT.xyz
Oct, 2022
可转移对话状态跟踪的模式编码
Schema Encoding for Transferable Dialogue State Tracking
HTML
PDF
Hyunmin Jeon, Gary Geunbae Lee
TL;DR
该论文提出了一种名为 SETDST 的基于神经网络的对话状态跟踪方法，通过对数据集的 schema 进行编码实现对新领域的有效迁移学习，进而提高多领域设置下的对话系统性能。
Abstract
dialogue state tracking
(DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep
neural models
for DST. However, the
→