W15-1501 |
on the popular skip-gram word
|
embedding
|
model . The novelty of our approach
|
S15-2155 |
work on using vector space word
|
embedding
|
models for hypernym-hyponym extraction
|
P14-1146 |
learning sentiment - specific word
|
embedding
|
( SSWE ) , which encodes sentiment
|
D15-1196 |
outperforms the state-of-the-art word
|
embedding
|
methods in both representation
|
W15-3820 |
performance of two state-of-the-art word
|
embedding
|
methods , namely word2vec and
|
D14-1012 |
effectively incorporating the word
|
embedding
|
features within the framework
|
D15-1183 |
writing styles , into the word
|
embedding
|
model . Since generative models
|
D14-1012 |
approaches can better utilize the word
|
embedding
|
features , among which the distributional
|
W15-2608 |
based approach that uses word
|
embedding
|
features to recognize drug names
|
W15-2619 |
rank synonym candidates with word
|
embedding
|
and pseudo-relevance feedback
|
W15-3041 |
and a feature produced with word
|
embedding
|
models ( SHEF - QuEst + + ) .
|