Book Image

Advanced Natural Language Processing with TensorFlow 2

By : Ashish Bansal, Tony Mullen
Book Image

Advanced Natural Language Processing with TensorFlow 2

By: Ashish Bansal, Tony Mullen

Overview of this book

Recently, there have been tremendous advances in NLP, and we are now moving from research labs into practical applications. This book comes with a perfect blend of both the theoretical and practical aspects of trending and complex NLP techniques. The book is focused on innovative applications in the field of NLP, language generation, and dialogue systems. It helps you apply the concepts of pre-processing text using techniques such as tokenization, parts of speech tagging, and lemmatization using popular libraries such as Stanford NLP and SpaCy. You will build Named Entity Recognition (NER) from scratch using Conditional Random Fields and Viterbi Decoding on top of RNNs. The book covers key emerging areas such as generating text for use in sentence completion and text summarization, bridging images and text by generating captions for images, and managing dialogue aspects of chatbots. You will learn how to apply transfer learning and fine-tuning using TensorFlow 2. Further, it covers practical techniques that can simplify the labelling of textual data. The book also has a working code that is adaptable to your use cases for each tech piece. By the end of the book, you will have an advanced knowledge of the tools, techniques and deep learning architecture used to solve complex NLP problems.
Table of Contents (13 chapters)
11
Other Books You May Enjoy
12
Index

Naïve-Bayes model for finding keywords

Building an NB model on this dataset takes under an hour and has the potential to significantly increase the quality and coverage of the labeling functions. The core model code for the NB model can be found in the spam-inspired-technique-naive-bayes.ipynb notebook. Note that these explorations are aside from the main labeling code, and this section can be skipped if desired, as the learnings from this section are applied to construct better labeling functions outlined in the snorkel-labeling.ipynb notebook.

The main flow of the NB-based exploration is to load the reviews, remove stop words, take the top 2,000 words to construct a simple vectorization scheme, and train an NB model. Since data loading is the same as covered in previous sections, the details are skipped in this section.

This section uses the NLTK and wordcloud Python packages. NLTK should already be installed as we have used it in Chapter 1, Essentials of...