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. The 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)
