arxivst stuff from arxiv that you should probably bookmark

End-to-End Multi-View Networks for Text Classification

Abstract · Apr 19, 2017 19:33 ·

views text emphasizes conneau mvn words sets concatenates view cs-cl cs-lg cs-ne

Arxiv Abstract

  • Hongyu Guo
  • Colin Cherry
  • Jiang Su

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.

Read the paper (pdf) »