Adaptive Sentence Boundary Disambiguation

Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-of-speech tagging and sentence alignment. Endof-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 e cient, 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 e cient and easily adaptable to di erent text genres, including single-case texts.