A00-1027 |
are extracted from hand-built
|
segmentation
|
dictionary . We selected nouns
|
A00-1027 |
accurate results . We need some good
|
segmentation
|
model for compound noun , therefore
|
A00-1027 |
Furthermore , accurate compound noun
|
segmentation
|
plays an important role in the
|
A00-1002 |
modify it or to reject it . The
|
segmentation
|
of a translation memory is a
|
A00-1027 |
paper presents two methods for
|
segmentation
|
of compound nouns . First , we
|
A00-1027 |
method of Korean compound noun
|
segmentation
|
based on lexical data extracted
|
A00-1027 |
treated as unseen words without a
|
segmentation
|
process . Furthermore , accurate
|
A00-1027 |
, therefore . In compound noun
|
segmentation
|
, the thing that we pay attention
|
A00-1027 |
are included in compound noun
|
segmentation
|
dictionary . There - fore , it
|
A00-1027 |
citations . <title> Compound Noun
|
Segmentation
|
Based on Lexical Data Extracted
|
A00-1027 |
constructed built-in dictionary for
|
segmentation
|
whose data were extracted from
|
A00-1027 |
data extracted from corpus . The
|
segmentation
|
is done by two steps : First
|
A00-1027 |
Extraction of Lexical Information for
|
Segmentation
|
from Corpus As we said earlier
|
A00-1027 |
nouns and construct the hand built
|
segmentation
|
dictionary with them . The dictionary
|
A00-1027 |
are about 100,000 . Second , the
|
segmentation
|
algorithm is applied if the compound
|
A00-1027 |
million word corpus . Second , a
|
segmentation
|
algorithm using statistical data
|
A00-1027 |
application system . Compound noun
|
segmentation
|
is necessarily required for improving
|
A00-1027 |
The first phase of compound noun
|
segmentation
|
uses the built-in dictionary
|
A00-1027 |
or phrase without its accurate
|
segmentation
|
. The problem in compound noun
|
A00-1027 |
built-in dictionary is that the
|
segmentation
|
could ( 1 ) be very accurate
|