Does tagging help parsing?

Atro Voutilainen
1998 Proceedings of the International Workshop on Finite State Methods in Natural Language Processing - FSMNLP '09   unpublished
7th floor) FIN-00014 University of Helsinki, F~,~l~n~[ • A~zo. Vou~ilaJ~enQllJ~g. hels~g]TA. Ii Abstract. The usefulness of POS taggere for syntactic parsing is a question little addressed in the literature. Because taggers reduce ambiguity from the parser's input, parsing is commonly supposed to become faster, and the result less ambiguous. On the other h~nd, tagging errors probably reduce the parser's recognition rate, so this drawback may outweigh the possible advantages. This paper
more » ... This paper empirically investigates these issues using two di~erent rule-based morphological dlsambiguators as preprocessor of a wide-coverage finite-state parser of English. With these rule-based taggers, the parser's output becomes less ambiguous without a considerable penalty to recognition rate. Parsing speed increases slightly, not decisively.
doi:10.3115/1611533.1611536 fatcat:pohyqmiqanhbnkbckszhd6qdi4