Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-ofspeech 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 efcient, trainable algorithm that uses a lexicon with part-of-speech probabilities and a feed-forward neural network. This work demonstrates the feasibility of using prior probabilities of part-of-speech assignments, as opposed to words or de nite part-ofspeech assignments, as contextual information. 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.