Unsupervised Training of a Finite-State Sliding-Window Part-of-Speech Tagger

A simple, robust sliding-window part-of-speech tagger is presented and a method is given to estimate its parameters from an untagged corpus. Its performance is compared to a standard Baum-Welchtrained hidden-Markov-model part-of-speech tagger. Transformation into a finite-state machine —behaving exactly as the tagger itself— is demonstrated.

• Type: Conference
• Year: 2004
• Where: TAL
• Authors: Enrique Sánchez Villamil, Mikel L. Forcada, Rafael C. Carrasco
• Keywords: Hidden-Markov-model Part-of-speech Tagger, Natural Language Processing, Part-of-speech Tagger, Sliding-window Part-of-speech Tagger, TAL 2004