Tagging French -- comparing a statistical and a constraint-based method
cmp-lg
2016-08-31 v1 Computation and Language
Abstract
In this paper we compare two competing approaches to part-of-speech tagging, statistical and constraint-based disambiguation, using French as our test language. 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 reasonably good, comparable to taggers for English. But the constraint-based tagger seems to be superior even with the limited time we allowed ourselves for rule development.
Cite
@article{arxiv.cmp-lg/9503003,
title = {Tagging French -- comparing a statistical and a constraint-based method},
author = {Jean-Pierre Chanod and Pasi Tapanainen},
journal= {arXiv preprint arXiv:cmp-lg/9503003},
year = {2016}
}
Comments
in Proceedings of EACL-95, uuencoded gzipped postscript