Automatic Refinement of a POS Tagger Using a Reliable Parser and Plain Text Corpora

This paper proposes a new unsupervised learning method for obtaining English part-ofspecch(POS) disambiguation rules which would improve thc accuracy of a POS tagger. This method has been implemented in the experimental system APRAS (Automatic POS Rule Acquisition System), which extracts POS disambiguation rules fl'om plain text corpora by utilizing different types of coded linguistic knowledge, i.e., POS tagging rules and syntactic parsing rules, which arc already stored in a fully implemented MT system.

• Type: Conference
• Year: 2000
• Where: COLING
• Authors: Hideki Hirakawa, Kenji Ono, Yumiko Yoshimura
• Keywords: COLING 2000, COLING 2008, Disambiguation Rules, POS Disambiguation Rules, POS Tagging Rules