基于依存句法的图注意力网络的方面级情感分析
首发时间:2021-04-13
摘要:方面级情感分析旨在对一句话中带有主观情感的词或者短语进行情感极性判断。现有的主流方法是基于注意力机制进行方面目标词的上下文语义提取,但是注意力机制对于位置信息不敏感,且不擅长捕获长距离的句法依赖信息,针对现有问题,本文提出一种特定方面的图注意力网络模型来弥补注意力机制的缺点。该模型先通过依存句法分析得到句子的依存句法树,再结合方面目标词在上下文的局部位置关系,生成带有局部位置信息的邻接矩阵,然后利用多层图注意力网络进行方面目标词的上下文语义提取,使得提取出来的方面目标的语义特征更加丰富,模型能更好的捕捉到远距离的依赖关系的同时也能捕捉方面词局部的信息。本文模型在5个基准数据集上均取得了较优的效果,通过模型对比和实验分析,证明了本文模型的有效性。
关键词: 自然语言处理 方面级情感分析 图注意力网络 依存句法分析
For information in English, please click here
Graph Attention Network with Dependency Syntax for Aspect level Sentiment Analysis
Abstract:The purpose of aspect level sentiment analysis is to judge the sentiment polarity of words or phrases with subjective emotions in a sentence. The existing mainstram method is to extract the context semantics of aspect targets words based on attention mechanism, but the attention mechanism is not sensitive to location information and is not good at capturing long-distance syntactic dependency information. To solve the existing problems, this paper proposes an aspect specific graph attention network model to make up for the shortcoming of attention mechanism. Firstly, the dependency syntax tree of a sentence is obtained by dependency parsing, and then the adjacency matrix with local location information is generated by combining the local location relationship of aspect target words in the context. Then the context semantics of aspect target words is extracted by multi-layer graph attention network, which makes the semantic features of extracted aspect targets more abundant. The model can better capture the long-distance syntactic dependency and also capture the local information of aspect words. The model has achieved better results on five benchmark data sets. The effectiveness of the model is verified by model comparision and experimental analysis.
Keywords: Natural language processing Aspect level sentiment analysis Graph attention network Dependency parsing
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于依存句法的图注意力网络的方面级情感分析
评论
全部评论0/1000