Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
This work addresses sentiment analysis for specific aspects in text, offering an incremental improvement by incorporating syntax structure into neural models.
The paper tackled aspect-level sentiment classification by proposing a target-dependent graph attention network (TD-GAT) that leverages dependency relationships among words, resulting in improved performance over baselines with GloVe embeddings and further gains when using BERT representations.
Aspect level sentiment classification aims to identify the sentiment expressed towards an aspect given a context sentence. Previous neural network based methods largely ignore the syntax structure in one sentence. In this paper, we propose a novel target-dependent graph attention network (TD-GAT) for aspect level sentiment classification, which explicitly utilizes the dependency relationship among words. Using the dependency graph, it propagates sentiment features directly from the syntactic context of an aspect target. In our experiments, we show our method outperforms multiple baselines with GloVe embeddings. We also demonstrate that using BERT representations further substantially boosts the performance.