计算机科学
对话框
推论
可解释性
编码
人工智能
情绪分析
话语
背景(考古学)
自然语言处理
机器学习
接头(建筑物)
任务(项目管理)
语音识别
建筑工程
经济
化学
管理
古生物学
万维网
生物化学
工程类
基因
生物
作者
Li Zheng,Fei Li,Yibo Chai,Chong Teng,Donghong Ji
标识
DOI:10.1007/978-3-031-44693-1_19
摘要
The joint task of Dialog Sentiment Classification (DSC) and Act Recognition (DAR) aims to predict the sentiment label and act label for each utterance in a dialog simultaneously. However, current methods encode the dialog context in only one direction, which limits their ability to thoroughly comprehend the context. Moreover, these methods overlook the explicit correlations between sentiment and act labels, which leads to an insufficient ability to capture rich sentiment and act clues and hinders effective and accurate reasoning. To address these issues, we propose a Bi-directional Multi-hop Inference Model (BMIM) that leverages a feature selection network and a bi-directional multi-hop inference network to iteratively extract and integrate rich sentiment and act clues in a bi-directional manner. We also employ contrastive learning and dual learning to explicitly model the correlations of sentiment and act labels. Our experiments on two widely-used datasets show that BMIM outperforms state-of-the-art baselines by at least 2.6% on F1 score in DAR and 1.4% on F1 score in DSC. Additionally, Our proposed model not only improves the performance but also enhances the interpretability of the joint sentiment and act prediction task.
科研通智能强力驱动
Strongly Powered by AbleSci AI