Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks

By Binxuan Huang, Kathleen M. Carley. Conference on Empirical Methods in Natural Language Processing, 2019

300 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e8ae7fcdc616353420f5cb115ed335ee382d384f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Uri Alon
2. Shaked Brody
3. Eran Yahav
4. Rui Wang
5. Xiaojun Quan
6. Kai Wang
7. Eduard H. Hovy
8. Hao Chen

Citations in the corpus

• How Attentive are Graph Attention Networks? (2021, background): “…et al.’s original design of GAT has spread to a variety of domains (Wang et al., 2019a; Qiu et al., 2018; Yang et al., 2020; Wang et al., 2019c; Huang and Carley, 2019; Ma et al., 2020; Kosaraju et al., 2019; Nathani et al., 2019; Wu et al., 2020; Zhang et al., 2020) and has become the…”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, methodology): “Following this line, a few works extend the GCN and GAT models by means of a syntactical dependency tree and develop several outstanding models (Zhang et al., 2019; Sun et al., 2019b; Huang and Carley, 2019; Wang et al., 2020; Tang et al., 2020).”
• Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020, background): “…sentiment analysis are used for comparison, including: • Syntax-aware models: LSTM+SynATT (He et al., 2018a), AdaRNN (Dong et al., 2014), PhraseRNN (Nguyen and Shirai, 2015), AS-GCN (Zhang et al., 2019), CDT (Sun et al., 2019b), GAT (Veliˇckovi´c et al., 2017) and TD-GAT (Huang and Carley, 2019).”
• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “• TD-GAT [29] exploits a target-dependent graph attention network to extract the dependency relationships among words.”