A Hierarchical Large-scale Knowledge Base for Measuring Semantic Similarity between Words.
|
Accession number;99A0263647
|
| Title;A Hierarchical Large-scale Knowledge Base for Measuring Semantic Similarity between Words. |
| Author;
HOKARI YUZURU
(Takushoku Univ., Fac. of Eng.)
ISHIKAWA TSUTOMU
(Takushoku Univ., Fac. of Eng.)
KASAHARA KANAME
(Nippon Telegr. and Teleph. Corp.)
|
Journal Title;IEIC Technical Report (Institute of Electronics, Information and Communication Engineers)
|
Journal Code:S0532B
|
ISSN:0913-5685
|
|
VOL.98;NO.498(AI98 62-67);PAGE.25-32(1999)
|
| Figure&Table&Reference;FIG.9, TBL.3, REF.12 |
| Pub. Country;Japan |
| Language;Japanese |
| Abstract;We have constructed a hierarchical large-scale knowledge base of words for measuring semantic similarity between words. This system consists of the basic knowledge base (GB1) of 40,000 Japanese daily-used words, the extended knowledge base (GB2) of 260,000 words based on Japanese-Dictionaries (KOUJIEN, DAIJIRIN) and the knowledge base (GB3) of Chinese characters based on a Chinese-Japanese dictionary, and the synonym dictionary(SD) of 7,000 words based on a Japanese dictionary. In the GB1, each word is represented by a series of weighted keywords. The keywords have some relationship with the word, and the weights of the keywords represent the degree of the strength of the relationship between the word and keywords. In the GB2, each word is represented by the word that is the most similar word to it in the GB1. The GB3 is used to form the series of weighted keywords of the word which is not contained in the GB1 and GB2. The SD consists of the number of groups used for judging whether or not two words are synonymous each other. (author abst.) |
|
|
|
Related Articles;
|
|
