Masafumi Hagiwara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Masafumi Hagiwara has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hiroaki Yamane
Keio University
3 shared publications Yuanzhi Ke
Department of Information and Computer Science Faculty of Science and Engineering Keio University Keio University Yokohama Japan
2 shared publicationsHajime Hotta
Faculty of Science and Technology, Keio University, JAPAN
1 shared publicationHitoshi Iyatomi
Department of Information and Computer Science, Keio University 3-14-1 Hiyoshi, Yokohama 223-8522, Japan
1 shared publicationKouhei Shimizu
Keio Univ, Dept Informat & Comp Sci, Kohoku Ku, 3-14-1 Hiyoshi, Yokohama, Kanagawa 2238522, Japan
1 shared publication- Takashi Hayashi
Department of Information and Computer Science, Keio University, 3‐14‐1 Hiyoshi, Yokohama 223‐8522, Japan
1 shared publication
Latest Publications
- 20 January 2019
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 23 (1) , 60-66
Analog Value Associative Memory Using Restricted Boltzmann Machine
Title: Analog Value Associative Memory Using Restricted Boltzmann Machine | Keywords: semantic network, Restricted Boltzmann Machine, word2vec, associative memory | Author: Yuichiro Tsutsui and Masafumi Hagiwara
- 20 January 2019
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 23 (1) , 60-66
Analog Value Associative Memory Using Restricted Boltzmann Machine
Title: Analog Value Associative Memory Using Restricted Boltzmann Machine | Keywords: semantic network, Restricted Boltzmann Machine, word2vec, associative memory | Author: Yuichiro Tsutsui and Masafumi Hagiwara
- Open Access
Improve Lexicon-based Word Embeddings By Word Sense Disambiguation
There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same likelihood, or minimize the distance between all of the synonym pairs in the lexicon. Such methods do not consider the relatedness and difference of the corpus and the lexicon, and may not be the best optimized. In this paper, we propose a novel method that considers the relatedness and difference of the corpus and the lexicon. It trains word embeddings by learning the corpus to predicate a word and its corresponding synonym under the context at the same time. For polysemous words, we use a word sense disambiguation filter to eliminate the synonyms that have different meanings for the context. To evaluate the proposed method, we compare the performance of the word embeddings trained by our proposed model, the control groups without the filter or the lexicon, and the prior works in the word similarity tasks and text classification task. The experimental results show that the proposed model provides better embeddings for polysemous words and improves the performance for text classification.
Open AccessImprove Lexicon-based Word Embeddings By Word Sense Disambiguation
There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same likelihood, or minimize the distance between all of the synonym pairs in the lexicon. Such methods do not consider the relatedness and difference of the corpus and the lexicon, and may not be the best optimized. In this paper, we propose a novel method that considers the relatedness and difference of the corpus and the lexicon. It trains word embeddings by learning the corpus to predicate a word and its corresponding synonym under the context at the same time. For polysemous words, we use a word sense disambiguation filter to eliminate the synonyms that have different meanings for the context. To evaluate the proposed method, we compare the performance of the word embeddings trained by our proposed model, the control groups without the filter or the lexicon, and the prior works in the word similarity tasks and text classification task. The experimental results show that the proposed model provides better embeddings for polysemous words and improves the performance for text classification.
- Open Access
Alleviating Overfitting for Polysemous Words for Word Representation Estimation Using Lexicons
Though there are some works on improving distributed word representations using lexicons, the improper overfitting of the words that have multiple meanings is a remaining issue deteriorating the learning when lexicons are used, which needs to be solved. An alternative method is to allocate a vector per sense instead of a vector per word. However, the word representations estimated in the former way are not as easy to use as the latter one. Our previous work uses a probabilistic method to alleviate the overfitting, but it is not robust with a small corpus. In this paper, we propose a new neural network to estimate distributed word representations using a lexicon and a corpus. We add a lexicon layer in the continuous bag-of-words model and a threshold node after the output of the lexicon layer. The threshold rejects the unreliable outputs of the lexicon layer that are less likely to be the same with their inputs. In this way, it alleviates the overfitting of the polysemous words. The proposed neural network can be trained using negative sampling, which maximizing the log probabilities of target words given the context words, by distinguishing the target words from random noises. We compare the proposed neural network with the continuous bag-of-words model, the other works improving it, and the previous works estimating distributed word representations using both a lexicon and a corpus. The experimental results show that the proposed neural network is more efficient and balanced for both semantic tasks and syntactic tasks than the previous works, and robust to the size of the corpus.
Open AccessAlleviating Overfitting for Polysemous Words for Word Representation Estimation Using Lexicons
Though there are some works on improving distributed word representations using lexicons, the improper overfitting of the words that have multiple meanings is a remaining issue deteriorating the learning when lexicons are used, which needs to be solved. An alternative method is to allocate a vector per sense instead of a vector per word. However, the word representations estimated in the former way are not as easy to use as the latter one. Our previous work uses a probabilistic method to alleviate the overfitting, but it is not robust with a small corpus. In this paper, we propose a new neural network to estimate distributed word representations using a lexicon and a corpus. We add a lexicon layer in the continuous bag-of-words model and a threshold node after the output of the lexicon layer. The threshold rejects the unreliable outputs of the lexicon layer that are less likely to be the same with their inputs. In this way, it alleviates the overfitting of the polysemous words. The proposed neural network can be trained using negative sampling, which maximizing the log probabilities of target words given the context words, by distinguishing the target words from random noises. We compare the proposed neural network with the continuous bag-of-words model, the other works improving it, and the previous works estimating distributed word representations using both a lexicon and a corpus. The experimental results show that the proposed neural network is more efficient and balanced for both semantic tasks and syntactic tasks than the previous works, and robust to the size of the corpus.
- 22 August 2014
- Published by Springer Nature in Soft Computing
- Vol. 19 (4) , 919-927
Oxymoron generation using an association word corpus and a large-scale N-gram corpus
- 22 August 2014
- Published by Springer Nature in Soft Computing
- Vol. 19 (4) , 919-927
Oxymoron generation using an association word corpus and a large-scale N-gram corpus
- 11 December 2013
- Published by Springer Nature in AI & SOCIETY
- Vol. 30 (1) , 57-67
Tag line generating system using knowledge extracted from statistical analyses
- 11 December 2013
- Published by Springer Nature in AI & SOCIETY
- Vol. 30 (1) , 57-67
Tag line generating system using knowledge extracted from statistical analyses
- Open Access
- 30 March 2012
- Published by Korean Institute of Intelligent Systems in International Journal of Fuzzy Logic and Intelligent Systems
- Vol. 12 (1) , 94-100
Web Catchphrase Improve System Employing Onomatopoeia and Large-Scale N-gram Corpus
- 30 March 2012
- Published by Korean Institute of Intelligent Systems in International Journal of Fuzzy Logic and Intelligent Systems
- Vol. 12 (1) , 94-100
Open AccessWeb Catchphrase Improve System Employing Onomatopoeia and Large-Scale N-gram Corpus
- 1 January 2011
- Published by Institute of Electrical Engineers of Japan (IEE Japan) in IEEJ Transactions on Electronics, Information and Systems
- Vol. 131 (3) , 551-557
Natural Language Processing Neural Network Considering Deep Cases
- 1 January 2011
- Published by Institute of Electrical Engineers of Japan (IEE Japan) in IEEJ Transactions on Electronics, Information and Systems
- Vol. 131 (3) , 551-557
Natural Language Processing Neural Network Considering Deep Cases
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10987584,p. 1-6
An Automatic KANSEI Fuzzy Rule Creating System Using Thesaurus
In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In Kansei Engineering, there are a lot of words for the expression of image. However, conventional methods cannot treat these words because it is too difficult to collect enough data of all words. The proposed system is an enhanced algorithm of the conventional method that the authors proposed. A set of fuzzy rules for only one impression word are extracted from the questionnaire responses by the conventional one. With the proposed system, sets of fuzzy rules for many words defined in the dictionary are extracted. The flow of the system consists of 3 steps: (1) calculation of the weights of thesaurus networks; (2) data collection; (3) extraction of fuzzy rules. Using a Japanese thesaurus dictionary, the sets of fuzzy rules for 1,195 impression words are extracted while the number of registered adjectives in the thesaurus is 2,822. From experimental results, the fuzzy rules extracted by the proposed system obtained higher accuracy than that extracted by the conventional one.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10987584,p. 1-6
An Automatic KANSEI Fuzzy Rule Creating System Using Thesaurus
In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In Kansei Engineering, there are a lot of words for the expression of image. However, conventional methods cannot treat these words because it is too difficult to collect enough data of all words. The proposed system is an enhanced algorithm of the conventional method that the authors proposed. A set of fuzzy rules for only one impression word are extracted from the questionnaire responses by the conventional one. With the proposed system, sets of fuzzy rules for many words defined in the dictionary are extracted. The flow of the system consists of 3 steps: (1) calculation of the weights of thesaurus networks; (2) data collection; (3) extraction of fuzzy rules. Using a Japanese thesaurus dictionary, the sets of fuzzy rules for 1,195 impression words are extracted while the number of registered adjectives in the thesaurus is 2,822. From experimental results, the fuzzy rules extracted by the proposed system obtained higher accuracy than that extracted by the conventional one.
- 20 May 2005
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 9 (3) , 304-313
A New Electronic Dictionary with Meaning Description of Case Frame
Welcome to the official website of Journal of Advanced Computational Intelligence and Intelligent Informatics.
- 20 May 2005
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 9 (3) , 304-313
A New Electronic Dictionary with Meaning Description of Case Frame
Welcome to the official website of Journal of Advanced Computational Intelligence and Intelligent Informatics.
- 24 September 2003
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 18 (11) , 1155-1172
Idea divergent editor using analogy: The IDEA system
- 24 September 2003
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 18 (11) , 1155-1172
Idea divergent editor using analogy: The IDEA system