Presentation 2013-10-19
Word sense disambiguation using dynamic contextual semantic network model and its improvement
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We proposed a method of word sense disambiguation using an Associative Concept Dictionary which includes semantic relations among concepts. In our previous researches, Dynamic Contextual Network Model were applied to neural networks, where the network structure changes according to the successive input words in the sentences. The model enhances the network dynamically by adding words successively from the input sentence until the model obtains a certain threshold to decide the appropriate meaning for the homographic ideograms. The new improved model disambiguates word senses using keyword following the ambiguous word when it finds misunderstanding of the disambiguation caused by the contextual information before the ambiguous word.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associative Concept Dictionary / Word Sense Disambiguation / Dynamic Contextual Network Model / Process Model of Language Understanding / Contextual Semantic Network
Paper # TL2013-44
Date of Issue

Conference Information
Committee TL
Conference Date 2013/10/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Word sense disambiguation using dynamic contextual semantic network model and its improvement
Sub Title (in English)
Keyword(1) Associative Concept Dictionary
Keyword(2) Word Sense Disambiguation
Keyword(3) Dynamic Contextual Network Model
Keyword(4) Process Model of Language Understanding
Keyword(5) Contextual Semantic Network
1st Author's Name Jun OKAMOTO
1st Author's Affiliation Faculty of Business innovation, Kaetsu University()
2nd Author's Name Shun ISHIZAKI
2nd Author's Affiliation Keio University
Date 2013-10-19
Paper # TL2013-44
Volume (vol) vol.113
Number (no) 253
Page pp.pp.-
#Pages 6
Date of Issue