Weak Supervision and Active Learning for Natural Language Processing

Abstract

Deep neural models in natural language processing rely on large amounts of labeled data. In the real world, annotation can be expensive and time consuming. In this project, the aim is to learn good deep neural models with a minimum amount of labeled data. We take multiple strategies to achieve this goal: we use structured information from the data, incorporate prior knowledge for the model and learn an active learning policy for annotation. Experiments on simulated and real word tasks show these strategies are useful and effective.