| tech,13-2-P06-2110,ak | Through two experiments , three methods for constructing <term> 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> . | #12444 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. |
