Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks

TL;DR

This paper introduces an attention-over-attention neural network for aspect-level sentiment classification, effectively modeling aspect-sentence interactions and improving performance over previous LSTM-based methods.

Contribution

The novel attention-over-attention (AOA) module explicitly captures aspect-sentence interactions and jointly learns their representations for better sentiment classification.

Findings

AOA outperforms previous LSTM-based models on benchmark datasets.

The model effectively captures important sentence parts relevant to aspects.

Joint learning of aspect and sentence representations improves accuracy.

Abstract

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.