Transformation Networks for Target-Oriented Sentiment Classification

TL;DR

This paper introduces a novel transformation network combining CNN and RNN layers for target-oriented sentiment classification, overcoming attention mechanism drawbacks and achieving state-of-the-art results.

Contribution

The paper proposes a new model that replaces attention with a CNN layer and a target-specific representation component, improving performance in sentiment classification.

Findings

Achieves new state-of-the-art on benchmark datasets.

Outperforms attention-based models in target-oriented sentiment tasks.

Effectively preserves contextual information while focusing on targets.

Abstract

Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model to overcome these issues. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer. Between the two layers, we propose a component to generate target-specific representations of words in the sentence, meanwhile incorporate a mechanism for preserving the original contextual information from the RNN layer. Experiments show that our model achieves a new state-of-the-art performance on a few benchmarks.