基于关系图注意力网络和宽度学习的负面情绪识别方法(Negative Emotion Recognition Method Based on Rational Graph Attention Network and Broad Learning)

Sancheng Peng (彭三城), Guanghao Chen (陈广豪), Lihong Cao (曹丽红), Rong Zeng (曾嵘), Yongmei Zhou (周咏梅), Xinguang Li (李心广)


Abstract
“对话文本负面情绪识别主要是从对话文本中识别出每个话语的负面情绪,近年来已成为了一个研究热点。然而,让机器在对话文本中识别负面情绪是一项具有挑战性的任务,因为人们在对话中的情感表达通常存在上下文关系。为了解决上述问题,本文提出一种基于关系图注意力网络(Rational Graph Attention Network, RGAT)和宽度学习(Broad Learning, BL)的对话文本负面情绪识别方法,即RGAT-BL。该方法采用预训练模型RoBERTa生成对话文本的初始向量;然后,采用Bi-LSTM对文本向量的局部特征和上下文语义特征进行提取,从而获取话语级别的特征;采用RGAT对说话者之间的长距离依赖关系进行提取,从而获取说话者级别的特征;采用BL对上述两种拼接后的特征进行处理,从而实现对负面情绪进行分类输出。通过在三种数据集上与基线模型进行对比实验,结果表明所提出的方法在三个数据集上的weighted-F 1、macroF 1值都优于基线模型。”
Anthology ID:
2022.ccl-1.44
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
485–496
Language:
Chinese
URL:
https://aclanthology.org/2022.ccl-1.44
DOI:
Bibkey:
Cite (ACL):
Sancheng Peng, Guanghao Chen, Lihong Cao, Rong Zeng, Yongmei Zhou, and Xinguang Li. 2022. 基于关系图注意力网络和宽度学习的负面情绪识别方法(Negative Emotion Recognition Method Based on Rational Graph Attention Network and Broad Learning). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 485–496, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
基于关系图注意力网络和宽度学习的负面情绪识别方法(Negative Emotion Recognition Method Based on Rational Graph Attention Network and Broad Learning) (Peng et al., CCL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ccl-1.44.pdf
Data
IEMOCAPMELD