Deep Learning for Information Extraction
This is the first part of a series of articles about Deep Learning methods for Natural Language Processing applications. As a use case I would like to walk you through the different aspects of Named Entity Recognition (NER), an important task of Information Extraction. In this first article I will give you an introduction to this topic. I will describe the baseline Deep Learning architecture for Named Entity Recognition, which is a bidirectional Recurrent Neural Network based on LSTM or GRU.