Interactive Attention Networks for Aspect-Level Sentiment Classification
This addresses the problem of more accurate sentiment analysis for specific aspects in text, though it is incremental over prior methods that focused on contexts.
The paper tackles aspect-level sentiment classification by proposing interactive attention networks (IAN) to separately model targets and contexts via interactive learning, achieving improved performance on SemEval 2014 datasets.
Aspect-level sentiment classification aims at identifying the sentiment polarity of specific target in its context. Previous approaches have realized the importance of targets in sentiment classification and developed various methods with the goal of precisely modeling their contexts via generating target-specific representations. However, these studies always ignore the separate modeling of targets. In this paper, we argue that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning. Then, we propose the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets, and generate the representations for targets and contexts separately. With this design, the IAN model can well represent a target and its collocative context, which is helpful to sentiment classification. Experimental results on SemEval 2014 Datasets demonstrate the effectiveness of our model.