Case Studies of NLP Features

Abstract

After discussing the different sources of information available for us for deriving features from natural language text, we will now explore examples of concrete NLP classification tasks, and suitable features for them. While the promise of neural networks is to alleviate the need for manual feature engineering, we still need to take these sources of information into consideration when designing our models: we want to make sure that the network we design can make effective use of the available signals, either by giving it direct access to them by use of feature-engineering; by designing the network architecture to expose the needed signals; or by adding them as an additional loss signals when training the models.