BriefGPT.xyz
Mar, 2020
用辅助说话人识别的多任务学习进行对话情感识别
Multi-Task Learning Network for Emotion Recognition in Conversation
HTML
PDF
Jingye Li, Meishan Zhang, Donghong Ji, Yijiang Liu
TL;DR
本文探讨了会话情感识别 (CER) 的问题，考虑到说话人的信息对于识别情感的影响，提出利用说话人鉴别任务 (SI) 辅助提升对话中话语的表示。实验结果表明，该方法能够有效提高 CER 的性能，达到了两个基准数据集的最优结果。
Abstract
conversational emotion recognition
(CER) has attracted increasing interests in the
natural language processing
(NLP) community. Different from the vanilla emotion recognition, effective speaker-sensitive
→