The "close-distant" relation of adjectival concepts based on self-organizing map

Authors:
Kyoko Kanzaki;Hitoshi Isahara;Noriko Tomuro
Affiliations:
National Institute of Information and Communications Technology, Sorakugun, Kyoto, Japan;National Institute of Information and Communications Technology, Sorakugun, Kyoto, Japan;DePaul University, Chicago, IL
Venue:
COGALEX '08 Proceedings of the workshop on Cognitive Aspects of the Lexicon
Year:
2008

Citing 6
Cited 0

Self-organizing maps

Self-organizing maps
Foundations of statistical natural language processing

Foundations of statistical natural language processing
Introduction to Modern Information Retrieval

Introduction to Modern Information Retrieval
Encoding information on adjectives in a lexical-semantic net for computational applications

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Concept discovery from text

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Modeling adjectives in computational relational lexica

COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we aim to detect some aspects of adjectival meanings. Concepts of adjectives are distributed by SOM (Self-Organizing map) whose feature vectors are calculated by MI (Mutual Information). For the SOM obtained, we make tight clusters from map nodes, calculated by cosine. In addition, the number of tight clusters obtained by cosine was increased using map nodes and Japanese thesaurus. As a result, the number of extended clusters of concepts was 149 clusters. From the map, we found 8 adjectival clusters in super-ordinate level and some tendencies of similar and dissimilar clusters.