|
Abstract : |
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. 1, |
