End-to-End Multi-View Networks for Text Classification
This work addresses text classification for NLP applications, representing an incremental improvement with specific performance gains.
The paper tackles text classification by proposing a multi-view network that automatically creates various attention-based views of input text, resulting in new state-of-the-art accuracies on two benchmark tasks.
We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features. For a bag-of-words representation, each view focuses on a different subset of the text's words. Aggregating many such views results in a more discriminative and robust representation. Through a novel architecture that both stacks and concatenates views, we produce a network that emphasizes both depth and width, allowing training to converge quickly. Using our multi-view architecture, we establish new state-of-the-art accuracies on two benchmark tasks.