Paper: Tagging French - Comparing A Statistical And A Constraint-Based Method

ACL ID E95-1021
Title Tagging French - Comparing A Statistical And A Constraint-Based Method
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 1995
Authors

In this paper we compare two compet- ing approaches to part-of-speech tagging, statistical and constraint-based disam- biguation, using French as our test lan- guage. We imposed a time limit on our experiment: the amount of time spent on the design of our constraint system was about the same as the time we used to train and test the easy-to-implement statistical model. We describe the two systems and compare the results. The accuracy of the statistical method is rea- sonably good, comparable to taggers for English. But the constraint-based tagger seems to be superior even with the lim- ited time we allowed ourselves for rule development.