Knowledge-driven Multi-Semantic Syntactic Interactions Model for Aspect-based Sentiment Analysis
In response to the problem of insufficient utilization of rich context information in sentiment classification tasks using graph convolutional networks,a knowledge-driven aspect based sentiment analysis model for multi-se-mantic syntactic interaction is proposed.Multiple semantic relationships between aspects and contexts are used to construct a multi-semantic relationship diagram,and external knowledge is used to construct an emotional dependen-cy diagram.In addition,a more advanced context representation is obtained by optimizing the attention mechanism.Then,different representations were fused.The experimental results on five public datasets show that the proposed model,KSSGCN_GloVe,has achieved an average improvement of 1.59％in accuracy and 3.17％in macro Fl com-pared to the baseline model ASGCN.
NETL
NSTL
万方数据
