摘要
情绪-原因对的自动抽取,是文本情感分析的新任务,旨在以子句为单位,从不带任何标注的原始文本中识别情绪表达,并确定产生相应情绪的原因,形成情绪-原因对。完成上述任务的关键是有效捕捉情绪和原因之间以及不同情绪-原因对之间的关联。针对现有研究在捕捉这些关联方面存在的粒度过粗、无法有效区分不同子句对之间因果关系的相互影响等不足,提出了一种基于异构图神经网络的情绪-原因对抽取方法。该方法首先构建以子句和子句对为顶点的异构图,其中子句和子句对之间以及不同的子句对之间存在不同类型的边,用于捕捉各种细粒度的关联;然后采用带有注意力机制的异构图神经网络顶点表达更新算法,对子句和子句对的初始表达进行迭代更新;接着将更新后的子句对表达输入到二元分类器,通过该分类器判断相应的子句对是否存在情绪-原因关系。在情绪-原因对抽取任务的基准数据集上进行的实验表明,所提基于异构图神经网络的方法具有稳定的效果提升,在F1值上比当前最好的方法高0.85%;如果底层编码器(用于得到初始的子句表达和子句对表达)采用BERT,F1值可以达73.12%,也优于底层编码器同样采用BERT的现有最新算法。
As an emerging task in text sentiment analysis,the automatic extraction of emotion-cause pairs aims to identify emotion expression from the raw texts without any annotation in the unit of clauses,and identify the causes for the corresponding emotions to form emotion-cause pairs.The crucial point of this task is focused on how to effectively capture the relationship between emotions and causes and among different emotion-cause pairs.To overcome the shortcomings of existing researches in capturing these associations,such as too coarse granularity and unable to effectively distinguish the mutual influence of causal relations between different pairs,this paper proposes an emotion-cause pair extraction method based on a heterogeneous graph neural network.Initially,we construct a heterogeneous graph with clauses and clause pairs as vertices,in which there are different types of edges between clauses and clause pairs and between different clause pairs to capture various fine-grained associations.Then using the heterogeneous graph neural network algorithm with attention mechanism to iteratively update the vertex embeddings of clauses and clause pairs.Finally,the updated embeddings is input to the binary classifier,and the classifier judges whether the corresponding pair has an emotion-cause relationship.To evaluate the effectiveness of the proposed model,we conduct a series of experiments on a benchmark dataset of the emotion-cause pair extraction task.The results demonstrate that the method based on the heterogeneous graph neural network proposed in this paper has a stable effect improvement,and the F1 value is 0.85% higher than the state-of-art baselines.When the bottom encoder(for obtaining the initial embeddings of clauses and clause pairs)is replaced by BERT,the F1 value can reach 73.12%,and our model also outperforms the state-of-art algorithm.
作者
蒲金垚
卜令梅
卢永美
叶子铭
陈黎
于中华
PU Jinyao;BU Lingmei;LU Yongmei;YE Ziming;CHEN Li;YU Zhonghua(School of Computer Science,Sichuan University,Chengdu 610045,China)
出处
《计算机科学》
CSCD
北大核心
2023年第1期205-212,共8页
Computer Science
基金
国家重点研发计划(2020YFB0704502)。
关键词
情感分析
情绪原因对抽取
异构图神经网络
图神经网络
Sentiment analysis
Emotion-Cause pair extraction
Heterogeneous graph neural network
Graph neural network
