J05-4002 |
we see potential for the use of
|
distributional similarity methods
|
in prepositional phrase attachment
|
J10-3003 |
attempting to move beyond a single-pass
|
distributional similarity method
|
. They propose a bootstrapping
|
C04-1146 |
on a potential application of
|
distributional similarity methods
|
. 6 Compositionality of collocations
|
J09-3004 |
applications . Comparative evaluations of
|
distributional similarity methods
|
for this type of application
|
C04-1146 |
this has on one application of
|
distributional similarity methods
|
( judging the compositionality
|
D11-1027 |
discourse relation predictions and
|
distributional similarity methods
|
in a global inference procedure
|
J05-4002 |
could be used to evaluate CRMs and
|
distributional similarity methods
|
in general . In particular ,
|
D12-1018 |
tackle an infamous property of
|
distributional similarity methods
|
, namely , the difficulty in
|
J09-3004 |
semantic similarity obtained by
|
distributional similarity methods
|
is insufficient quality of the
|
J05-4002 |
al. ( 2004 ) investigate using
|
distributional similarity methods
|
to find predominant word senses
|
J09-3004 |
, those candidate pairs of the
|
distributional similarity method
|
for which entailment holds at
|
N10-3005 |
Evaluation Issues 4.1 Task Vector-based
|
distributional similarity methods
|
have proven to be a valuable
|
N09-2008 |
search engine . 2 Related work
|
Distributional similarity methods
|
model the similarity or relatedness
|
D11-1027 |
separate components and focused
|
distributional similarity methods
|
collected about event pairs as
|
N10-1010 |
standard ones than traditional
|
distributional similarity methods
|
. Despite that , our evaluation
|
D11-1027 |
supervised approach , based on focused
|
distributional similarity methods
|
and discourse connectives , for
|
N10-1010 |
taxonomic relations than traditional
|
distributional similarity methods
|
, which associate each target
|
N10-1013 |
simple modifications to standard
|
distributional similarity methods
|
such as those presented by Curran
|
E09-1064 |
and resources based on automatic
|
distributional similarity methods
|
( Lin , 1998 ; Pantel and Lin
|
D13-1171 |
2008 ) . Brown clustering is a
|
distributional similarity method
|
that merges pairs of word clusters
|