Book Review: Biomedical Natural Language Processing by Kevin Bretonnel Cohen and Dina Demner-Fushman

Book Reviews Biomedical Natural Language Processing Kevin Bretonnel Cohen and Dina Demner-Fushman (University of Colorado School of Medicine, and National Library of Medicine) John Benjamins Publishing (Book series on Natural Language Processing, edited by Ruslan Mitkov, volume 11), 2014, 160 pp; hardbound, ISBN 978-90-272-4997-5 Reviewed by Jin-Dong Kim Database Center for Life Science The book begins with a declaration that “the intended audience of the book is natural language processing specialists who want to move into the biomedical domain.” It is indeed a great introductory textbook to the field of biomedical natural language processing (NLP), particularly for NLP specialists. Browsing the contents, many NLP specialists will find the titles of chapters familiar: “Named Entity Recognition,” “Rela- tion Extraction,” and so on. Those familiar topics are reformulated in the context of bio- medical informatics, with rich biomedical examples and a good amount of explanation. One of the most important characteristics of the book is that it is very easy to read. Because biomedical NLP is an interdisciplinary area, the quality of this kind of authoring counts on the depth of authors’ insight into the relevant subject areas, which include NLP, bioinformatics, medical science, and linguistics. The level of clarity and conciseness throughout the book demonstrates that the authors have a clear and deep understanding of these areas. Complex technical details are successfully distilled into abstract ideas which are at a level that can be understood without much prior knowledge. It is an obviously important feature of an introductory textbook. Because of the ease of reading, I think the book is a good introductory resource even for non- NLP specialists (e.g., bioinformaticians who want to make use of NLP resources). Another notable characteristic of the book is that bio- and medical NLP are equally importantly described. Although biomedical NLP is often referred to as one subject area, the community has been quite divided into bio- and medical NLP, and it is in fact a rare chance to learn about both at the same time. The importance of understanding both is very well described in Chapter 2.3, “Clinical Text Mining,” in the context of translational research. In following sections, I add more detailed reviews on individual chapters. For convenience of review, I take the liberty of dividing the chapters into three parts. 1. Part I. Introductory Materials (Chapters 1 and 2) Simply speaking, for NLP specialists, entering into biomedical NLP means a change of the type of texts that are going to be dealt with. In this sense, Chapter 1, “Introduction to Natural Language Processing,” is an ideal starting point, presenting the characteristics doi:10.1162/COLI r 00281 © 2017 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 43, Number 1 of various types of biomedical texts and the language in them. Chapter 2, “Historical Background,” presents a concise history of the field. Seamlessly interweaving relevant parts of the history of biomedical informatics and biomedical NLP, it is a masterpiece of introduction to the …

Content truncated to 500 words