CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
This work addresses a specific bottleneck in fine-grained sentiment analysis for NLP applications, but it is incremental as it builds on existing attention-based methods.
The paper tackled the problem of noise in attention mechanisms for multi-aspect sentiment analysis by proposing constrained attention networks (CAN) with orthogonal and sparse regularization, resulting in outperforming state-of-the-art methods on two public datasets.
Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating aspect-specific sentence representations. However, the attention may inherently introduce noise and downgrade the performance. In this paper, we propose constrained attention networks (CAN), a simple yet effective solution, to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism. Specifically, we introduce orthogonal regularization on multiple aspects and sparse regularization on each single aspect. Experimental results on two public datasets demonstrate the effectiveness of our approach. We further extend our approach to multi-task settings and outperform the state-of-the-art methods.