Pierre M. Nugues – författare

Since the last edition of this book (2014), progress has been astonishing in all areas of Natural Language Processing, with recent achievements in Text Generation that spurred a media interest going beyond the traditional academic circles.

Since the last edition of this book (2014), progress has been astonishing in all areas of Natural Language Processing, with recent achievements in Text Generation that spurred a media interest going beyond the traditional academic circles. Text Processing has meanwhile become a mainstream industrial tool that is used, to various extents, by countless companies. As such, a revision of this book was deemed necessary to catch up with the recent breakthroughs, and the author discusses models and architectures that have been instrumental in the recent progress of Natural Language Processing.As in the first two editions, the intention is to expose the reader to the theories used in Natural Language Processing, and to programming examples that are essential for a deep understanding of the concepts. Although present in the previous two editions, Machine Learning is now even more pregnant, having replaced many of the earlier techniques to process text. Many new techniques build on the availability of text. Using Python notebooks, the reader will be able to load small corpora, format text, apply the models through executing pieces of code, gradually discover the theoretical parts by possibly modifying the code or the parameters, and traverse theories and concrete problems through a constant interaction between the user and the machine. The data sizes and hardware requirements are kept to a reasonable minimum so that a user can see instantly, or at least quickly, the results of most experiments on most machines.The book does not assume a deep knowledge of Python, and an introduction to this language aimed at Text Processing is given in Ch. 2, which will enable the reader to touch all the programming concepts, including NumPy arrays and PyTorch tensors as fundamental structures to represent and process numerical data in Python, or Keras for training Neural Networks to classify texts. Covering topics like Word Segmentation and Part-of-Speech and Sequence Annotation, the textbook also gives an in-depth overview of Transformers (for instance, BERT), Self-Attention and Sequence-to-Sequence Architectures.

The areas of natural language processing and computational linguistics have continued to grow in recent years, driven by the demand to automatically process text and spoken data. With the processing power and techniques now available, research is scaling up from lab prototypes to real-world, proven applications.This book teaches the principles of natural language processing, first covering linguistics issues such as encoding, entropy, and annotation schemes; defining words, tokens and parts of speech; and morphology. It then details the language-processing functions involved, including part-of-speech tagging using rules and stochastic techniques; using Prolog to write phase-structure grammars; parsing techniques and syntactic formalisms; semantics, predicate logic and lexical semantics; and analysis of discourse, and applications in dialog systems. The key feature of the book is the author's hands-on approach throughout, with extensive exercises, sample code in Prolog and Perl, and a detailed introduction to Prolog. The reader is supported with a companion website that contains teaching slides, programs, and additional material. The book is suitable for researchers and students of natural language processing and computational linguistics.