Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks
This work addresses sentiment analysis for specific aspects in text, offering a novel method for a known bottleneck in natural language processing.
The paper tackles aspect-level sentiment classification by introducing an attention-over-attention neural network to model interactions between aspects and sentences, achieving improved performance over previous LSTM-based methods on laptop and restaurant datasets.
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.