The sensitivity of belief networks to im
โ
A. Pradhan; M. Henrion; G. Provan; B. del Favero; K. Huang
๐
Article
๐
1996
๐
Elsevier Science
๐
English
โ 90 KB
We consider what tagging models are most appropriate as front ends for probabilistic context-free grammar parsers. In particular, we ask if using a "multiple tagger", a tagger that returns more than one tag, improves parsing performance. Our conclusion is somewhat surprising: single-tag Markov-mode