Zero-shot Aspect-level Sentiment Classification via Explicit Utilization of Aspect-to-Document Sentiment Composition
This work addresses the problem of expensive aspect-level labeling for sentiment analysis, offering a zero-shot solution that is incremental by building on existing composition ideas.
The paper tackles zero-shot aspect-level sentiment classification by using only document-level reviews, proposing the AF-DSC method to model sentiment composition, and achieves state-of-the-art results with only 30k training data, outperforming previous methods that used millions of data.
As aspect-level sentiment labels are expensive and labor-intensive to acquire, zero-shot aspect-level sentiment classification is proposed to learn classifiers applicable to new domains without using any annotated aspect-level data. In contrast, document-level sentiment data with ratings are more easily accessible. In this work, we achieve zero-shot aspect-level sentiment classification by only using document-level reviews. Our key intuition is that the sentiment representation of a document is composed of the sentiment representations of all the aspects of that document. Based on this, we propose the AF-DSC method to explicitly model such sentiment composition in reviews. AF-DSC first learns sentiment representations for all potential aspects and then aggregates aspect-level sentiments into a document-level one to perform document-level sentiment classification. In this way, we obtain the aspect-level sentiment classifier as the by-product of the document-level sentiment classifier. Experimental results on aspect-level sentiment classification benchmarks demonstrate the effectiveness of explicit utilization of sentiment composition in document-level sentiment classification. Our model with only 30k training data outperforms previous work utilizing millions of data.