P15-1107 |
that hierarchically builds an
|
embedding
|
for a paragraph from embeddings
|
P15-1104 |
the supervised data to find an
|
embedding
|
subspace that fits the task complexity
|
C88-1033 |
reformulated as the problem of finding an
|
embedding
|
function f from the representational
|
P98-2242 |
given , which are realised in an
|
embedding
|
algorithm . The significant aspect
|
W03-2200 |
embedding discussed here is an
|
embedding
|
or an enrichment of MT by combining
|
P15-2048 |
labels . Specifically , we learn an
|
embedding
|
for each label and each feature
|
P13-2087 |
labeled data , and produces an
|
embedding
|
in the same space , but with
|
P15-1167 |
Abstract This paper proposes an
|
embedding
|
matching approach to Chinese
|
D15-1232 |
words , where we assume that an
|
embedding
|
of each word can represent its
|
J13-1008 |
complex syntactic patterns , and
|
embedding
|
useful morphological features
|
S15-2085 |
, word prior polarities , and
|
embedding
|
clusters . Using weighted Support
|
D14-1113 |
word sense discrimination and
|
embedding
|
learning , by non-parametrically
|
J92-4004 |
Grammars ( TAG ) in such a manner and
|
embedding
|
it in a unification-based framework
|
P98-1097 |
is to exploit term overlap and
|
embedding
|
so as to yield a substantial
|
P15-1049 |
discover the power of statistical and
|
embedding
|
features . However , tree-based
|
J88-2001 |
event-related information from text and
|
embedding
|
those methods in question-answering
|
D15-1153 |
way to combine traditional and
|
embedding
|
features compared with previous
|
W10-4104 |
other examples of this section are
|
embedding
|
, while this example is of overlapping
|
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
|