Placement of nouns in a multi-dimensional space based on words' cooccurrency

Yoichi Tomiura, Shosaku Tanaka, Toru Hitaka

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The semantic similarity (or distance) between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity (or distance) based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. This paper proposes a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that "vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space". Although the whole meaning of nouns isn't reflected in the word vectors obtained by the pro posed method, the semantic similarity (or distance) between nouns defined with the word vectors is proper for an example-based disambiguation method. Copyright (c) 2004 JSAI.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume19
Issue number1
DOIs
Publication statusPublished - 2004

Fingerprint

Semantics
Glossaries
Principal component analysis
Processing

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Placement of nouns in a multi-dimensional space based on words' cooccurrency. / Tomiura, Yoichi; Tanaka, Shosaku; Hitaka, Toru.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 19, No. 1, 2004, p. 1-9.

Research output: Contribution to journalArticle

@article{0b0f7f81bacc4f6fbb5bb8835fa9d3c5,
title = "Placement of nouns in a multi-dimensional space based on words' cooccurrency",
abstract = "The semantic similarity (or distance) between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity (or distance) based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. This paper proposes a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that {"}vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space{"}. Although the whole meaning of nouns isn't reflected in the word vectors obtained by the pro posed method, the semantic similarity (or distance) between nouns defined with the word vectors is proper for an example-based disambiguation method. Copyright (c) 2004 JSAI.",
author = "Yoichi Tomiura and Shosaku Tanaka and Toru Hitaka",
year = "2004",
doi = "10.1527/tjsai.19.1",
language = "English",
volume = "19",
pages = "1--9",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - Placement of nouns in a multi-dimensional space based on words' cooccurrency

AU - Tomiura, Yoichi

AU - Tanaka, Shosaku

AU - Hitaka, Toru

PY - 2004

Y1 - 2004

N2 - The semantic similarity (or distance) between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity (or distance) based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. This paper proposes a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that "vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space". Although the whole meaning of nouns isn't reflected in the word vectors obtained by the pro posed method, the semantic similarity (or distance) between nouns defined with the word vectors is proper for an example-based disambiguation method. Copyright (c) 2004 JSAI.

AB - The semantic similarity (or distance) between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity (or distance) based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. This paper proposes a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that "vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space". Although the whole meaning of nouns isn't reflected in the word vectors obtained by the pro posed method, the semantic similarity (or distance) between nouns defined with the word vectors is proper for an example-based disambiguation method. Copyright (c) 2004 JSAI.

UR - http://www.scopus.com/inward/record.url?scp=18444405837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18444405837&partnerID=8YFLogxK

U2 - 10.1527/tjsai.19.1

DO - 10.1527/tjsai.19.1

M3 - Article

AN - SCOPUS:18444405837

VL - 19

SP - 1

EP - 9

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -