D09-1072 |
acquisition with the learning of a
|
POS disambiguation
|
model . Moreover , the disambiguation
|
P07-1094 |
) . All of this work is really
|
POS disambiguation
|
: learning is strongly constrained
|
J02-1004 |
lexical patterns as a context for
|
POS disambiguation
|
. As mentioned earlier , because
|
D09-1072 |
Simple Unsupervised Learner for
|
POS Disambiguation
|
Given Only a Minimal Lexicon
|
D15-1273 |
categorial method . As with the
|
PoS disambiguation
|
task , the topological method
|
J02-1004 |
into morphological analysis and
|
POS disambiguation
|
systems . POS disambiguation
|
E14-3013 |
error types , we should perform
|
PoS disambiguation
|
since the same surface form could
|
N01-1015 |
- verbs , etc. . The need for
|
POS disambiguation
|
is even clearer for languages
|
J02-1004 |
linguistic contexts necessary for
|
POS disambiguation
|
. Also , approaches using only
|
E99-1018 |
for future research . <title>
|
POS Disambiguation
|
and Unknown Word Guessing with
|
P02-1056 |
After morphological processing ,
|
POS disambiguation
|
rules are applied which compute
|
E99-1018 |
achieving -- 5,5 % error rate for
|
POS disambiguation
|
and -- 16 % error rate for unknown
|
P07-1094 |
hope to unify the problems of
|
POS disambiguation
|
and syntactic clustering by presenting
|
C02-1071 |
) andusethatinforma - tion for
|
PoS disambiguation
|
. This interaction of PoS disambiguation
|
E06-1034 |
tagging distinctions affect the
|
POS disambiguation
|
task , in section 5 we modify
|
P06-1041 |
sequences are anal - ysed and
|
POS disambiguation
|
is part of the task to be solved
|
J02-1004 |
and POS disambiguation systems .
|
POS disambiguation
|
has usually been performed by
|
J02-1004 |
statistical and rule-based approaches to
|
POS disambiguation
|
and can be tightly coupled with
|
P06-2045 |
approach was used to solve the
|
POS disambiguation
|
and unknown word guessing in
|
D09-1072 |
the unsupervised learning of a
|
POS disambiguation
|
model , and in most previous
|