Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans
This work addresses a specific challenge in natural language processing for sentiment analysis, offering an incremental improvement over previous attention-based models.
The paper tackles the problem of aspect-based sentiment analysis by proposing a structured attention model that extracts aspect-specific opinion spans to predict sentiment polarity, achieving effective results on four datasets.
Aspect based sentiment analysis, predicting sentiment polarity of given aspects, has drawn extensive attention. Previous attention-based models emphasize using aspect semantics to help extract opinion features for classification. However, these works are either not able to capture opinion spans as a whole, or not able to capture variable-length opinion spans. In this paper, we present a neat and effective structured attention model by aggregating multiple linear-chain CRFs. Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features. The experimental results on four datasets demonstrate the effectiveness of the proposed model, and our analysis demonstrates that our model can capture aspect-specific opinion spans.