Attention Transfer Network for Aspect-level Sentiment Classification
This work addresses data scarcity issues in ASC, which is a domain-specific problem for sentiment analysis, and is incremental as it builds on existing attention mechanisms by transferring knowledge from related tasks.
The paper tackles the problem of data scarcity in aspect-level sentiment classification (ASC) by proposing an Attention Transfer Network (ATN) that transfers attention knowledge from resource-rich document-level datasets, resulting in consistent outperformance of state-of-the-art methods on benchmark datasets.
Aspect-level sentiment classification (ASC) aims to detect the sentiment polarity of a given opinion target in a sentence. In neural network-based methods for ASC, most works employ the attention mechanism to capture the corresponding sentiment words of the opinion target, then aggregate them as evidence to infer the sentiment of the target. However, aspect-level datasets are all relatively small-scale due to the complexity of annotation. Data scarcity causes the attention mechanism sometimes to fail to focus on the corresponding sentiment words of the target, which finally weakens the performance of neural models. To address the issue, we propose a novel Attention Transfer Network (ATN) in this paper, which can successfully exploit attention knowledge from resource-rich document-level sentiment classification datasets to improve the attention capability of the aspect-level sentiment classification task. In the ATN model, we design two different methods to transfer attention knowledge and conduct experiments on two ASC benchmark datasets. Extensive experimental results show that our methods consistently outperform state-of-the-art works. Further analysis also validates the effectiveness of ATN.