#27345In this paper we compare two competing approaches topart-of-speech tagging, statistical and constraint-based disambiguation, using French as our test language.
tech,12-1-E95-1021,ak
<term>
part-of-speech tagging
</term>
,
<term>
statistical and constraint-based disambiguation
</term>
, using
<term>
French
</term>
as our
<term>
#27348In this paper we compare two competing approaches to part-of-speech tagging,statistical and constraint-based disambiguation, using French as our test language.
other,14-4-E95-1021,ak
comparable to
<term>
taggers
</term>
for
<term>
English
</term>
. But the
<term>
constraint-based tagger
#27423The accuracy of the statistical method is reasonably good, comparable to taggers forEnglish.
model,36-2-E95-1021,ak
train and test the easy-to-implement
<term>
statistical model
</term>
. We describe the two
<term>
systems
#27396We 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-implementstatistical model.
other,21-1-E95-1021,ak
</term>
, using
<term>
French
</term>
as our
<term>
test language
</term>
. We imposed a time limit on our
#27357In this paper we compare two competing approaches to part-of-speech tagging, statistical and constraint-based disambiguation, using French as ourtest language.
other,17-5-E95-1021,ak
limited time we allowed ourselves for
<term>
rule development
</term>
. We provide a unified account of
#27442But the constraint-based tagger seems to be superior even with the limited time we allowed ourselves forrule development.
other,18-1-E95-1021,ak
constraint-based disambiguation
</term>
, using
<term>
French
</term>
as our
<term>
test language
</term>
.
#27354In this paper we compare two competing approaches to part-of-speech tagging, statistical and constraint-based disambiguation, usingFrench as our test language.
tech,4-4-E95-1021,ak
results . The
<term>
accuracy
</term>
of the
<term>
statistical method
</term>
is reasonably good , comparable to
#27413The accuracy of thestatistical method is reasonably good, comparable to taggers for English.
measure(ment),1-4-E95-1021,ak
</term>
and compare the results . The
<term>
accuracy
</term>
of the
<term>
statistical method
</term>
#27410Theaccuracy 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
#27427But theconstraint-based tagger seems to be superior even with the limited time we allowed ourselves for rule development.
tech,19-2-E95-1021,ak
of time spent on the design of our
<term>
constraint system
</term>
was about the same as the time we
#27379We imposed a time limit on our experiment: the amount of time spent on the design of ourconstraint system was about the same as the time we used to train and test the easy-to-implement statistical model.