Adaptive Sentence Boundary Disambiguation

dc.creatorPalmer, David D.
dc.creatorHearst, Marti A.
dc.date1994-11-16
dc.date1994-11-22
dc.date.accessioned2026-07-07T08:58:38Z
dc.date.available2026-07-07T08:58:38Z
dc.descriptionLabeling 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.
dc.descriptionThis 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
dc.identifierhttps://arxiv.org/abs/cmp-lg/9411022
dc.identifierhttp://arxiv.org/abs/cmp-lg/9411022
dc.identifierProceedings of ANLP 94
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/147403
dc.subjectComputation and Language
dc.titleAdaptive Sentence Boundary Disambiguation
dc.typetext

Files

Collections