W15-3820 |
representations , also known as word
|
embedding
|
, have been shown to improve
|
W15-3820 |
performance of two state-of-the-art word
|
embedding
|
methods , namely word2vec and
|
W15-3822 |
method called Surrounding based
|
embedding
|
feature ( SBE ) , and two newly
|
W15-3822 |
: Left-Right surrounding based
|
embedding
|
feature ( LR_SBE ) and MAX surrounding
|
W15-3822 |
LR_SBE ) and MAX surrounding based
|
embedding
|
feature ( MAX_SBE ) . We then
|
W15-3822 |
Minnesota showed that neural word
|
embedding
|
features improved the performance
|
W15-4005 |
regression to learn the bilingual word
|
embedding
|
using compositional distributional
|
W15-4310 |
representation . Besides word
|
embedding
|
, we use partof-speech ( POS
|
W96-0413 |
set for the same variable in the
|
embedding
|
structure . An inner quantifier
|
W97-0901 |
reports on SRA 's experience in
|
embedding
|
name recognition in these three
|
W98-1311 |
Another aspect to consider is the
|
embedding
|
of the single elements of the
|