representation methods for text data including both traditional statistical models and newer deep learning based embedding models. Techniques around parsing and processing text data have also been improved with some new methods. Considering popular NLP applications, for text classification, we also cover methods for tuning and improving our models. Text Summarization has gone through a major overhaul in the context of topic models where we showcase how to build, tune and interpret topic models in the context of an interest dataset on NIPS conference papers. Similarly, we cover text similarity techniques with a real-world example of movie recommenders. Sentiment Analysis is covered in-depth with both supervised and unsupervised techniques. We also cover both machine learning and deep learning models for supervised sentiment analysis. Semantic Analysis gets its own dedicated chapter where we also showcase how you can build your own Named Entity Recognition (NER) system from scratch. To conclude things, we also have a completely new chapter on the promised of Deep Learning for NLP where we also showcase a hands-on example on deep transfer learning. While the overall structure of the book remains the same, the entire code base, modules, and chapters will be updated to the latest Python 3.x release. ---------------------------------- Also the key selling points • Implementations are based on Python 3.x and state-of-the-art popular open source libraries in NLP • Covers Machine Learning and Deep Learning for Advanced Text Analytics and NLP • Showcases diverse NLP applications including Classification, Clustering, Similarity Recommenders, Topic Models, Sentiment and Semantic Analysis. |