Presentation | 2006-03-16 Learning Abstract Concepts and Words from Perception Based on Bayesian Model Selection Naoto IWAHASHI, Ken SATOH, Hideki ASOH, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We address the computational mechanism that enables machines to learn words for abstract concepts not formed directly from perceived features. The learning is done based on the structured basic concepts that are formed directly from perceived features. The lexicon is represented by a graphical model that includes information about word meanings grounded on perceived features and the relationship between the words. The computation mechanism makes it possible for a machine to interpret and learn a presented new word by selecting one from among the multiple candidates for an extended lexicon, which are generated by adding the word and its possible meanings into the lexicon that has been learned before. Learning of model parameters is done by variational Bayesian methods. Experimental results show that the computational mechanism successfully learned abstract word meanings. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Abstract concept / Perception / Machine learning / Model selection / Bayesian criteria / Variational Bayes |
Paper # | PRMU2005-234 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2006/3/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Learning Abstract Concepts and Words from Perception Based on Bayesian Model Selection |
Sub Title (in English) | |
Keyword(1) | Abstract concept |
Keyword(2) | Perception |
Keyword(3) | Machine learning |
Keyword(4) | Model selection |
Keyword(5) | Bayesian criteria |
Keyword(6) | Variational Bayes |
1st Author's Name | Naoto IWAHASHI |
1st Author's Affiliation | Advanced Telecommunications Research Institute International() |
2nd Author's Name | Ken SATOH |
2nd Author's Affiliation | National Institute of Informatics |
3rd Author's Name | Hideki ASOH |
3rd Author's Affiliation | National Institute of Advanced Industrial Science and Technology |
Date | 2006-03-16 |
Paper # | PRMU2005-234 |
Volume (vol) | vol.105 |
Number (no) | 673 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |