BriefGPT.xyz
Jun, 2021
HERALD: 一种在社交对话中高效检测用户脱离的注释方法
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations
HTML
PDF
Weixin Liang, Kai-Hui Liang, Zhou Yu
TL;DR
本研究提出HERALD框架，并将训练数据注释过程重新定位为去噪问题，以提高注释效率和检测用户不参与的准确度。实验表明，该框架在两个对话语料库中能够达到86％的用户不参与检测准确率。
Abstract
open-domain dialog systems
have a user-centric goal: to provide humans with an engaging conversation experience.
user engagement
is one of the most important metrics for evaluating
→