Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Natural language understanding in a semantic web context
Barrière C., Springer International Publishing, New York, NY, 2016. 317 pp. Type: Book (978-3-319413-35-8)
Date Reviewed: Aug 18 2017

We continue to witness increasing interest in natural language processing (NLP) since its beginning in 1950 when Alan Turing developed the Turing test--a test of a machine’s ability to exhibit intelligent behavior through a conversation with a human being equivalent to, or indistinguishable from, that of a human. Currently, almost all services on the web can benefit from NLP. Often even simple basic NLP methods can improve information processing, which is inevitable for many tasks either in e-shops, news portals, or social networks. This book, as the preface states, “serves as a good starting point for students and researchers in [the] semantic web interested in discovering what natural language processing has to offer.”

In the context of this book, natural language understanding is understood as a knowledge acquisition process that can help us distill semantic information from text data. For this purpose, the book introduces a reader to several key NLP concepts that can help him/her reach this goal. However, I have found the book title to be misleading. Natural language understanding as a part of NLP is generally used for full understanding of text meaning, for example, comprehension of a directive for a robot. This book is far from that. It is a very good introductory text useful either for those interested in NLP basics or for the semantic web community, as the author recommends. To be precise, the book is on Information extraction, which is part of NLP.

The book is divided into four parts, each concerned with one high-level task. Parts are further divided into chapters, with each one providing theoretical background for smaller tasks along with small-scale experiments, a list of further reading, and several exercises for readers. The first two parts of the book are concerned with basic NLP concepts such as surface forms of words, text corpora, and N-gram model. These are absolutely necessary tools for any NLP research, and this book does a good job explaining them to novices. Throughout the book, the author proposes numerous experiments. These are introduced with a goal and a measure of success. Then, the solution is proposed and results are reported. This simple pipeline can help the reader to realize how to approach verification for various NLP tasks they are reading about. Moreover, this approach is used not only for NLP-related tasks, but can be used more broadly in other tasks related to information processing.

The third and fourth parts of the book are concerned with “Semantic Grounding” and “Knowledge Acquisition,” respectively. These parts are more advanced because they are built on established material from the previous two parts. The reader is introduced to such tasks as word sense disambiguation, relatedness measuring, relation extraction, linguistic and semantic role labeling, and so on. These are all semantic-oriented NLP tasks that can help us extract knowledge about entities from a text. The author even mentioned a state-of-the-art word embedding technique based on neural networks.

The book provides an extensive glossary of terms. Because the book does not delve deeply into linguistics, the glossary is very useful, especially for NLP novice readers.

I appreciate the breadth and coverage approach combined with fresh and intuitive text supplemented by many examples from the very beginning. The focus is on language analysis as opposed to mathematical models, so it does not assume any preexisting knowledge of advanced mathematics.

The expected audience of this book is graduate students or researchers wishing to get an overview of NLP focusing on information extraction. It is written with care, easily readable and well suited for learning. From a methodological point of view, a young researcher can use the experimentation methodology excellently presented throughout the book outside of NLP as well.

The book covers “traditional NLP,” which is still of high importance. For those who want to discover recent trends in NLP, I would recommend extending this reading with material on machine and deep learning approaches. (This will require advanced mathematics.)

Reviewer:  M. Bielikova Review #: CR145493 (1710-0652)
Bookmark and Share
 
Natural Language Processing (I.2.7 )
 
 
Semantic Networks (I.2.4 ... )
 
 
World Wide Web (WWW) (H.3.4 ... )
 
 
Knowledge Representation Formalisms And Methods (I.2.4 )
 
 
Systems And Software (H.3.4 )
 
Would you recommend this review?
yes
no
Other reviews under "Natural Language Processing": Date
Current research in natural language generation
Dale R. (ed), Mellish C. (ed), Zock M., Academic Press Prof., Inc., San Diego, CA, 1990. Type: Book (9780122007354)
Nov 1 1992
Incremental interpretation
Pereira F., Pollack M. Artificial Intelligence 50(1): 37-82, 1991. Type: Article
Aug 1 1992
Natural language and computational linguistics
Beardon C., Lumsden D., Holmes G., Ellis Horwood, Upper Saddle River, NJ, 1991. Type: Book (9780136128137)
Jul 1 1992
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy