Adaptive Sentence Boundary Disambiguation
Abstract
Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-of-speech tagging and sentence alignment. End-of-sentence punctuation marks are ambiguous; to disambiguate them most systems use brittle, special-purpose regular expression grammars and exception rules. As an alternative, we have developed an efficient, trainable algorithm that uses a lexicon with part-of-speech probabilities and a feed-forward neural network. After training for less than one minute, the method correctly labels over 98.5\% of sentence boundaries in a corpus of over 27,000 sentence-boundary marks. We show the method to be efficient and easily adaptable to different text genres, including single-case texts.
Cite
@article{arxiv.cmp-lg/9411022,
title = {Adaptive Sentence Boundary Disambiguation},
author = {David D. Palmer and Marti A. Hearst},
journal= {arXiv preprint arXiv:cmp-lg/9411022},
year = {2008}
}
Comments
This is a Latex version of the previously submitted ps file (formatted as a uuencoded gz-compressed .tar file created by csh script). The software from the work described in this paper is available by contacting dpalmer@cs.berkeley.edu