Co-occurrence Vectors from Corpora vs. Distance Vectors from Dictionaries

COLING94, 304-309. A comparison was made of vectors derived by using ordinary co-occurrence statistics from large text corpora and of vectors derived by measuring the inter-word distances in dictionary definitions. The precision of word sense disambiguation by using co-occurrence vectors from the 19...

Full description

Saved in:
Bibliographic Details
Main Authors Niwa, Yoshiki, Nitta, Yoshihiko
Format Journal Article
LanguageEnglish
Published 01.04.1995
Subjects
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:COLING94, 304-309. A comparison was made of vectors derived by using ordinary co-occurrence statistics from large text corpora and of vectors derived by measuring the inter-word distances in dictionary definitions. The precision of word sense disambiguation by using co-occurrence vectors from the 1987 Wall Street Journal (20M total words) was higher than that by using distance vectors from the Collins English Dictionary (60K head words + 1.6M definition words). However, other experimental results suggest that distance vectors contain some different semantic information from co-occurrence vectors.
Bibliography:ARL Research Report No. 94-003
DOI:10.48550/arxiv.cmp-lg/9503025