other,32-2-P06-2110,bq |
Through two experiments , three
<term>
methods for constructing word vectors
</term>
, i.e. ,
<term>
LSA-based , cooccurrence-based and dictionary-based methods
</term>
, were compared in terms of the ability to represent two kinds of
<term>
similarity
</term>
, i.e. ,
<term>
taxonomic similarity
</term>
and
<term>
associative similarity
</term>
.
|
#11526
Through two experiments, three methods for constructing word vectors, i.e., LSA-based, cooccurrence-based and dictionary-based methods, were compared in terms of the ability to represent two kinds of similarity , i.e., taxonomic similarity and associative similarity. |