Paper: Unsupervised Learning Of Syntactic Knowledge: Methods And Measures

ACL ID W96-0203
Title Unsupervised Learning Of Syntactic Knowledge: Methods And Measures
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 1996
Authors

Supervised methods for ambiguity resolution learn in "sterile" environments, in absence of syntactic noise. However, in many language engineering applications manually tagged corpora are not available nor easily implemented. On the other side, the "exportability" of disambiguation cues acquired from a given, noise-free, domain (e.g. the Wall Street Journal) to other domains is not obvious. Unsupervised methods of lexical learning have, just as well, many inherent limitations. First, the type of syntactic ambiguity phenomena occurring in real do- mains are much more complex than the standard V N PP patterns analyzed in literature. Second, espe- cially in sublanguages, syntactic noise seems to be a systematic phenomenon, because many ambiguities oc- cur within identical phrases. In such case...