Paper: Does Baum-Welch Re-Estimation Help Taggers?

ACL ID A94-1009
Title Does Baum-Welch Re-Estimation Help Taggers?
Venue Applied Natural Language Processing Conference
Session Main Conference
Year 1994
Authors

In part of speech tagging by Hidden Markov Model, a statistical model is used to assign grammatical categories to words in a text. Early work in the field re- lied on a corpus which had been tagged by a human annotator to train the model. More recently, Cutting et al. (1992) sug- gest that training can be achieved with a minimal lexicon and a limited amount of a priori information about probabilities, by using an Baum-Welch re-estimation to automatically refine the model. In this paper, I report two experiments designed to determine how much manual training information is needed. The first exper- iment suggests that initial biasing of ei- ther lexical or transition probabilities is es- sential to achieve a good accuracy. The second experiment reveals that there are three distinct patterns ...