| tech,9-1-E95-1021,ak | compare two competing approaches to <term> | part-of-speech tagging | </term> , <term> statistical and constraint-based | #27345 In this paper we compare two competing approaches to part-of-speech tagging , statistical and constraint-based disambiguation, using French as our test language. | |
| model,36-2-E95-1021,ak | train and test the easy-to-implement <term> | statistical model | </term> . We describe the two <term> systems | #27396 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 . | |
| tech,4-4-E95-1021,ak | . The <term> accuracy </term> of the <term> | statistical method | </term> is reasonably good , comparable | #27413 The accuracy of the statistical method is reasonably good, comparable to taggers for English. | |
| tech,2-5-E95-1021,ak | </term> for <term> English </term> . But the <term> | constraint-based tagger | </term> seems to be superior even with the | #27427 But the constraint-based tagger seems to be superior even with the limited time we allowed ourselves for rule development. |
