© 2012

Coarse-to-Fine Natural Language Processing

  • Foreword written by Eugene Charniak

  • This book describes a particular approach to natural language processing and its applications to several tasks

  • Many applications are presented


Table of contents

  1. Front Matter
    Pages i-xxii
  2. Slav Petrov
    Pages 1-6
  3. Slav Petrov
    Pages 47-67
  4. Slav Petrov
    Pages 99-100
  5. Back Matter
    Pages 101-105

About this book


The impact of computer systems that can understand natural language will be tremendous. To develop this capability we need to be able to automatically and efficiently analyze large amounts of text. Manually devised rules are not sufficient to provide coverage to handle the complex structure of natural language, necessitating systems that can automatically learn from examples. To handle the flexibility of natural language, it has become standard practice to use statistical models, which assign probabilities for example to the different meanings of a word or the plausibility of grammatical constructions.

This book develops a general coarse-to-fine framework for learning and inference in large statistical models for natural language processing.

Coarse-to-fine approaches exploit a sequence of models which introduce complexity gradually. At the top of the sequence is a trivial model in which learning and inference are both cheap. Each subsequent model refines the previous one, until a final, full-complexity model is reached. Applications of this framework to syntactic parsing, speech recognition and machine translation are presented, demonstrating the effectiveness of the approach in terms of accuracy and speed. This book is intended for students and researchers interested in statistical approaches to Natural Language Processing. 

Slav’s work Coarse-to-Fine Natural Language Processing represents a major advance in the area of syntactic parsing, and a great advertisement for the superiority of the machine-learning approach.

Eugene Charniak (Brown University)


68T50 Computational Linguistics Machine Learning Natural Language Processing

Authors and affiliations

  1. 1.GoogleNew YorkUSA

About the authors

Slav Petrov is a Research Scientist at Google New York. He works on problems at the intersection of natural language processing and machine learning. In particular, he is interested in syntactic parsing and its applications to machine translation and information extraction. He also teaches Statistical Natural Language Processing at New York University as an Adjunct Professor.

Bibliographic information

  • Book Title Coarse-to-Fine Natural Language Processing
  • Authors Slav Petrov
  • Series Title Theory and Applications of Natural Language Processing
  • Series Abbreviated Title Theory,Applicat. Natural Language Processing
  • DOI
  • Copyright Information Springer-Verlag Berlin Heidelberg 2012
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Computer Science Computer Science (R0)
  • Hardcover ISBN 978-3-642-22742-4
  • Softcover ISBN 978-3-642-42749-7
  • eBook ISBN 978-3-642-22743-1
  • Series ISSN 2192-032X
  • Series E-ISSN 2192-0338
  • Edition Number 1
  • Number of Pages XXII, 106
  • Number of Illustrations 0 b/w illustrations, 0 illustrations in colour
  • Topics Computer Science, general
  • Buy this book on publisher's site
Industry Sectors
Chemical Manufacturing
IT & Software
Consumer Packaged Goods