Christof Monz

In: Journal of Logic, Language and Information, Kluwer Academic Publishers, pages

The book is a slightly revised version of the author's dissertation at the Carnegie Mellon University in 1995. It is very well written and contrary to a lot of the literature in statistical linguistics, not overloaded with formulas and diagrams. The theoretical results are well motivated and most of the time their presentation is accompanied by a short prose explanation. Although the book is better suited for people with some background in statistical linguistics, it is not totally inaccessible to students who only have some background in probability theory. Common concepts from statistical linguistics used throughout the book, are shortly explained. The explanations may be not long enough, if one has never heard of these concepts before, but it is not the aim of the book to be a textbook on statistical linguistics. The aim is to show how a particular method, namely the loglinear method, allows for a statistical approach to ambiguity resolution.

[ PostScript | PostScript (gnu-zipped) | PDF ]

@Article{monz:98review,
  author =       {Monz, Christof},
  title =        {Review of Alexander Franz: Automatic Ambiguity 
                  Resolution in Natural Language Processing: 
                  An Empirical Approach},
  journal =      {Journal of Logic, Language and Information},
  year =         {to appear}
}