Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks
About
Aspect-level sentiment classification aims to identify the sentiment expressed towards some aspects given context sentences. In this paper, we introduce an attention-over-attention (AOA) neural network for aspect level sentiment classification. Our approach models aspects and sentences in a joint way and explicitly captures the interaction between aspects and context sentences. With the AOA module, our model jointly learns the representations for aspects and sentences, and automatically focuses on the important parts in sentences. Our experiments on laptop and restaurant datasets demonstrate our approach outperforms previous LSTM-based architectures.
Binxuan Huang, Yanglan Ou, Kathleen M. Carley• 2018
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Aspect-level sentiment classification | SemEval Restaurant 2014 (test) | Accuracy81.2 | 67 | |
| Aspect-level sentiment classification | SemEval Laptop 2014 (test) | Accuracy74.5 | 59 | |
| Aspect-based Sentiment Classification | Lap14 | Accuracy72.62 | 37 | |
| Aspect-level Sentiment Analysis | Rest 14 | Accuracy79.97 | 25 | |
| Aspect-level Sentiment Analysis | Rest15 | Accuracy78.17 | 23 | |
| Aspect-level Sentiment Analysis | Rest16 | Accuracy87.5 | 22 |
Showing 6 of 6 rows