W99-0630 |
most cases , the precision of
|
lexicon merging
|
obtained from anti-lexicon are
|
W99-0630 |
lexicons . Finally , in addition to
|
lexicon merging
|
, POS mapping table is also useful
|
W99-0630 |
conservative lexeme selection during the
|
lexicon merging
|
process . Moreover , our model
|
E12-1056 |
coverage that can be achieved by
|
lexicon merging
|
. In order to validate our claim
|
W99-0630 |
Results We obtain the results on
|
lexicon merging
|
as shown at table 5 . The anti-lexicon
|
W99-0630 |
using anti-lexicon is lower in
|
lexicon merging
|
than in POS mapping rule learning
|
W99-0630 |
table 8 . The best precision for
|
lexicon merging
|
is obtained from T = 0.8 and
|
W99-0630 |
lexicons we can test twelve pairwise
|
lexicon merging
|
tasks , as shown in table 3 .
|
W99-0630 |
mapping rules at all to tackle the
|
lexicon merging
|
problems . Our next step will
|
W99-0630 |
experiments showing low precision on
|
lexicon merging
|
even using the human-generated
|
W99-0630 |
mapping rules is 8 % , but for
|
lexicon merging
|
it improves to about 22 % . Recall
|
W99-0630 |
lexemes in RL . I e ' r recall on
|
lexicon merging
|
= I 5.2 Results We obtain the
|
W99-0630 |
in each testing task using the
|
lexicon merging
|
algorithm described above , and
|
W99-0630 |
merged lexicons . Most of the 12
|
lexicon merging
|
tasks achieve nearly more than
|
W99-0630 |
anti-threshold to smaller value . 4
|
Lexicon merging
|
algorithm Given a POS mapping
|
W10-2505 |
essential and difficult problem of
|
lexicon merging
|
, namely how to carry over the
|
W99-0630 |
the following : ELF precision on
|
lexicon merging
|
eL where • EL is the set
|
W99-0630 |
define the precision and recall on
|
lexicon merging
|
as the following : ELF precision
|
W99-0630 |
) } end end end Algorithm 3 :
|
Lexicon merging
|
algorithm by the fact that machine
|
W99-0630 |
affect the precision and recall on
|
lexicon merging
|
, we also ran experiments using
|