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)
Other Books You May Enjoy

Data loading and pre-processing

There are several summarization-related datasets available for training. These datasets are available through the TensorFlow Datasets or tfds package, which we have used in the previous chapters as well. The datasets that are available differ in length and style. The CNN/DailyMail dataset is one of the most commonly used datasets. It was published in 2015, with approximately a total of 1 million news articles. Articles from CNN, starting in 2007, and Daily Mail, starting in 2010, were collected until 2015. The summaries are usually multi-sentence. The Newsroom dataset, available from, contains over 1.3 million news articles from 38 publications. However, this dataset requires that you register to download it, which is why it is not used in this book. The wikiHow data set contains full Wikipedia article pages and the summary sentences for those articles. The LCSTS data set contains Chinese language data collected from Sina...