#3288A novelbootstrapping approach to Named Entity (NE) tagging using concept-based seeds and successive learners is presented.
tech,1-3-N03-2025,ak
woman for
<term>
PERSON NE
</term>
. The
<term>
bootstrapping procedure
</term>
is implemented as training two
<term>
#3336Thebootstrapping procedure is implemented as training two successive learners.
other,15-2-N03-2025,ak
seeds
</term>
that correspond to the
<term>
concept
</term>
for the targeted
<term>
NE
</term>
,
#3321This approach only requires a few common noun or pronoun seeds that correspond to theconcept for the targeted NE, e.g. he/she/man/woman for PERSON NE.
model,12-1-N03-2025,ak
Entity ( NE ) tagging
</term>
using
<term>
concept-based seeds
</term>
and
<term>
successive learners
</term>
#3298A novel bootstrapping approach to Named Entity (NE) tagging usingconcept-based seeds and successive learners is presented.
lr,10-5-N03-2025,ak
Markov Model
</term>
is trained on a
<term>
corpus
</term>
automatically tagged by the first
#3369Then, a Hidden Markov Model is trained on acorpus automatically tagged by the first learner.
tech,2-4-N03-2025,ak
successive learners
</term>
. First ,
<term>
decision list
</term>
is used to learn the
<term>
parsing-based
#3348First,decision list is used to learn the parsing-based NE rules.
tech,3-5-N03-2025,ak
parsing-based NE rules
</term>
. Then , a
<term>
Hidden Markov Model
</term>
is trained on a
<term>
corpus
</term>
#3362Then, aHidden Markov Model is trained on a corpus automatically tagged by the first learner.
tech,16-5-N03-2025,ak
</term>
automatically tagged by the first
<term>
learner
</term>
. The resulting
<term>
NE system
</term>
#3375Then, a Hidden Markov Model is trained on a corpus automatically tagged by the firstlearner.
tech,5-1-N03-2025,ak
<term>
bootstrapping approach
</term>
to
<term>
Named Entity ( NE ) tagging
</term>
using
<term>
concept-based seeds
</term>
#3291A novel bootstrapping approach toNamed Entity ( NE ) tagging using concept-based seeds and successive learners is presented.
other,19-2-N03-2025,ak
<term>
concept
</term>
for the targeted
<term>
NE
</term>
, e.g. he/she/man / woman for
<term>
#3325This approach only requires a few common noun or pronoun seeds that correspond to the concept for the targetedNE, e.g. he/she/man/woman for PERSON NE.
tech,2-6-N03-2025,ak
<term>
learner
</term>
. The resulting
<term>
NE system
</term>
approaches
<term>
supervised NE performance
#3379The resultingNE system approaches supervised NE performance for some NE types.
other,10-6-N03-2025,ak
supervised NE performance
</term>
for some
<term>
NE types
</term>
. In this paper , we describe a
<term>
#3387The resulting NE system approaches supervised NE performance for someNE types.
model,7-2-N03-2025,ak
approach only requires a few common
<term>
noun or pronoun seeds
</term>
that correspond to the
<term>
concept
#3313This approach only requires a few commonnoun or pronoun seeds that correspond to the concept for the targeted NE, e.g. he/she/man/woman for PERSON NE.
model,9-4-N03-2025,ak
decision list
</term>
is used to learn the
<term>
parsing-based NE rules
</term>
. Then , a
<term>
Hidden Markov Model
#3355First, decision list is used to learn theparsing-based NE rules.
other,26-2-N03-2025,ak
</term>
, e.g. he/she/man / woman for
<term>
PERSON NE
</term>
. The
<term>
bootstrapping procedure
#3332This approach only requires a few common noun or pronoun seeds that correspond to the concept for the targeted NE, e.g. he/she/man/woman forPERSON NE.
tech,15-1-N03-2025,ak
<term>
concept-based seeds
</term>
and
<term>
successive learners
</term>
is presented . This approach only
#3301A novel bootstrapping approach to Named Entity (NE) tagging using concept-based seeds andsuccessive learners is presented.
tech,8-3-N03-2025,ak
</term>
is implemented as training two
<term>
successive learners
</term>
. First ,
<term>
decision list
</term>
#3343The bootstrapping procedure is implemented as training twosuccessive learners.
measure(ment),5-6-N03-2025,ak
resulting
<term>
NE system
</term>
approaches
<term>
supervised NE performance
</term>
for some
<term>
NE types
</term>
. In
#3382The resulting NE system approachessupervised NE performance for some NE types.