From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation
This addresses sentiment analysis for long documents, offering an incremental improvement through discourse augmentation.
The paper tackles sentiment analysis for long documents by proposing a framework that combines a sentiment-dependent discourse treebank with a hybrid TreeLSTM hierarchical attention model, showing performance improvements over previous discourse-based approaches.
Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.