Publishing type：Research paper (international conference proceedings)   Publisher：INCOMA Ltd.  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2021

Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics  

DOI： 10.18653/v1/2021.eacl-main.4

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/eacl/2021

Publishing type：Research paper (international conference proceedings)   Publisher：INCOMA Ltd.  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2021

Publishing type：Research paper (international conference proceedings)   Publisher：INCOMA Ltd.  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2021

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

Pointer-generator, which is the one of the strong baselines in neural summarization models, generates summaries by selecting words from a set of words (output vocabulary) and words in source documents. A conventional method for constructing output vocabulary collects highly frequent words in summaries of training data. However, highly frequent words in summaries could be usually a high possibility to be frequent in source documents. Thus, an output vocabulary constructed by the conventional method is redundant for pointer-generator because pointergenerator can copy words in source documents. We propose a vocabulary construction method that selects words included in each summary but not included in its source text of each pair. Experimental results on CNN/Daily Mail corpus and NEWSROOM corpus showed that our method contributes to improved ROUGE scores while obtaining high ratios of generating novel words that do not occur in source documents.

DOI： 10.1527/tjsai.35-6_b-k46

CiNii Research

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ijcnlp/2020

Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics  

DOI： 10.18653/v1/p19-1099

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/acl/2019-1

Language：Japanese   Publisher：Association for Computational Linguistics  

We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical compound name paraphrase model. Our method enables the NER model to capture chemical compound paraphrases by sharing the parameters of NER and the character embeddings based on long short-term memories (LSTM) with the paraphrase model. Experimental results on BioCreative IV CHEMDNER show that our method learning paraphrase contributes to improved accuracy.

DOI： 10.18653/v1/D19-1648

CiNii Research

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/emnlp/emnlp2019-1.html#WatanabeTNMI19

Publishing type：Research paper (international conference proceedings)   Publisher：INCOMA Ltd.  

DOI： 10.26615/978-954-452-056-4_093

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/ranlp/ranlp2019.html#MoritaI19

Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics  

DOI： 10.18653/v1/k18-1052

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/conll/2018

Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/coling/2018d

Publishing type：Research paper (international conference proceedings)   Publisher：European Language Resources Association (ELRA)  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/lrec/2018

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-030-03520-4_7

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/airs/airs2018.html#MakinoNYISI18

Publishing type：Research paper (scientific journal)  

DOI： 10.1145/3218820

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：INCOMA Ltd.  

DOI： 10.26615/978-954-452-049-6_097

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/ranlp/ranlp2017.html#TokunagaNI17

Publishing type：Research paper (international conference proceedings)  

DOI： 10.1007/978-3-319-57529-2_21

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/pakdd/pakdd2017-2.html#Iwakura17

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-319-70145-5_2

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/airs/airs2017.html#MakinoI17

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-319-42911-3_53

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/pricai/pricai2016.html#YoshikawaI16

Language：Japanese   Publisher：Springer  

We propose an Frequently Asked Question (FAQ) search method that uses a document classifier for classifying a natural language query to a corresponding FAQ. The document classifier classifies a query with words that occur in the query. However, since FAQs have little redundancy, using FAQs as training data for the document classifier is not sufficient for classifying queries that have the similar meaning but different surface expressions. To tackle this problem, our method generates training data automatically from FAQs and corresponding histories and trains the document classifier with them. Furthermore, with the automatically generated training data, our method learns a ranking model that uses classification results of the document classifier. Experimental results on a company FAQs and corresponding histories showed that our method outperformed pseudo-relevance feedback and query expansion model that uses word alignment model in statistical machine translation.

DOI： 10.1007/978-3-319-42911-3_25

CiNii Research

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/pricai/pricai2016.html#MakinoNI16

Publishing type：Research paper (international conference proceedings)   Publisher：The COLING 2016 Organizing Committee  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/acl-alr/2016

Language：Japanese   Publisher：Association for Computational Linguistics  

This paper introduces a Japanese Named Entity (NE) corpus of various genres. We annotated 136 documents in the Balanced Corpus of Contemporary Written Japanese with the eight types of NE tags defined by IREX. The NE corpus consists of six types of genres of documents such as blogs, magazines, white papers, and so on. The corpus contains 2,464 NE tags in total.

DOI： 10.18653/v1/W16-2706

CiNii Research

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/aclnews/aclnews2016.html#IwakuraKT16

Publishing type：Research paper (international conference proceedings)   Publisher：The Association for Computer Linguistics  

DOI： 10.18653/v1/w16-1708

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/acllaw/2016

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-319-13560-1_62

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/pricai/pricai2014.html#IwakuraSO14

Publishing type：Research paper (international conference proceedings)   Publisher：National Institute of Informatics (NII)  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ntcir/2013

Publishing type：Research paper (scientific journal)  

DOI： 10.1145/2499955.2499958

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：IEEE Computer Society  

DOI： 10.1109/IV.2013.69

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/iv/iv2013.html#OkuboIM13

Publishing type：Research paper (international conference proceedings)   Publisher：ACL  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/conll/2013

Publishing type：Research paper (international conference proceedings)   Publisher：RANLP 2013 Organising Committee / ACL  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2013

Language：Japanese   Publishing type：Research paper (scientific journal)  

CiNii Research

researchmap

Other Link： http://id.ndl.go.jp/bib/024148834

Publishing type：Research paper (international conference proceedings)   Publisher：The Association for Computer Linguistics  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ijcnlp/2011

Publishing type：Research paper (international conference proceedings)   Publisher：RANLP 2011 Organising Committee  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2011

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-642-12116-6_18

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/cicling/cicling2010.html#Iwakura10

Language：Japanese   Publisher：The Institute of Electrical Engineers of Japan  

AdaBoost is a method to create a final hypothesis by repeatedly generating a weak hypothesis in each training iteration with a given weak learner. AdaBoost-based algorithms are successfully applied to several tasks such as Natural Language Processing (NLP), OCR, and so on. However, learning on the training data consisting of large number of samples and features requires long training time. We propose a fast AdaBoost-based algorithm for learning rules represented by combination of features. Our algorithm constructs a final hypothesis by learning several weak-hypotheses at each iteration. We assign a confidence-rated value to each weak-hypothesis while ensuring a reduction in the theoretical upper bound of the training error of AdaBoost. We evaluate our methods with English POS tagging and text chunking. The experimental results show that the training speed of our algorithm are about 25 times faster than an AdaBoost-based learner, and about 50 times faster than Support Vector Machines with polynomial kernel on the average while maintaining state-of-the-art accuracy.

DOI： 10.1541/ieejeiss.130.83

CiNii Research

researchmap

Other Link： http://id.ndl.go.jp/bib/10539443

Language：Japanese   Publishing type：Research paper (scientific journal)  

CiNii Research

researchmap

Other Link： http://id.ndl.go.jp/bib/024206504

Publishing type：Research paper (international conference proceedings)   Publisher：RANLP 2009 Organising Committee / ACL  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/ranlp/2009

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-642-02556-3_39

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/hci/hci2009-8.html#AndoSIO09

Publishing type：Research paper (scientific journal)  

DOI： 10.17562/pb-40-5

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

CiNii Research

researchmap

Other Link： http://id.ndl.go.jp/bib/024268976

Publishing type：Research paper (international conference proceedings)   Publisher：ACL  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/conll/2008

Language：English   Publishing type：Research paper (scientific journal)  

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-540-73354-6_5

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/hci/hci2007-9.html#IwakuraO07

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computational Linguistics (ACL)  

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)   Publisher：Springer  

DOI： 10.1007/978-3-540-74827-4_154

researchmap

Other Link： https://dblp.uni-trier.de/db/conf/kes/kes2007-2.html#IwakuraUO07

Publishing type：Research paper (international conference proceedings)  

DOI： 10.3115/1118984.1118986

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/acl-iwp/2003

Publishing type：Research paper (international conference proceedings)  

researchmap

Other Link： https://dblp.uni-trier.de/rec/conf/nlprs/2001

DOI： 10.48550/arXiv.2409.06216

researchmap

J-GLOBAL

researchmap

DOI： 10.48550/arXiv.2304.10813

researchmap

DOI： 10.48550/arXiv.2304.10808

researchmap

J-GLOBAL

researchmap

Language：Japanese   Publisher：The Association for Natural Language Processing  

DOI： 10.5715/jnlp.27.969

CiNii Research

researchmap

Other Link： http://id.ndl.go.jp/bib/031204649

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

In this paper, we investigate of using subword sequences for compound name extraction problem. Five variety of subword sequence generators (SYMBOL, SP, BPE, BPE-DICT, and BPE-PMI) were used in the investigation. Last two of these, BPE-DICT and BPE-PMI, are originally proposed in this work. BPE-DICT is a variation of BPE which has a dictionary-based restriction. BPE-PMI introduces the PMI measure instead of word frequency count. The experimental results showed that subword sequence information improved the extraction performance. The F-measure value of BPE-DICT is 86.74 which is best score in all conditions of our experiments.

DOI： 10.11517/pjsai.jsai2019.0_1n4j903

CiNii Research

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

In this paper, we propose a BiLSTM-CRF model for extracting compound names from documents in chemical domain. The proposed model can be taken multiple subword sequences as input in order to obtain sufficient features for long span or unknown tokens. Subword LSTM units with contextual information are introduced in the input layer of the model. We conducted experiments based on CHEMDNER challenge to investigate the effectiveness of the model. As a result, the extraction accuracy outperformed the normal BiLSTM-CRF model, and experimental results on unknown words showed that the proposed method works better.

DOI： 10.11517/pjsai.jsai2019.0_1n4j902

CiNii Research

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

In this paper, we propose to use self-training for chemical named entity recognition. We first train a neural network-based model for chemical named entity recognition model using the CHEMDNER corpus. The trained model is used to annotate the unlabelled MEDLINE corpus to create automatically labelled training data. We then use both training data, manually labelled CHEMNER corpus and automatically labelled MEDLINE corpus, to train our final model. The evaluation using the unlabelled MEDLINE corpus as test data showed that the effectiveness of self-training in the chemical named entity recognition task.

DOI： 10.11517/pjsai.jsai2019.0_1n4j901

CiNii Research

researchmap

Language：Japanese  

DOI： 10.15084/00001494

CiNii Research

researchmap

Language：Japanese  

CiNii Research

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

DOI： 10.11517/jjsai.29.5_439

CiNii Research

researchmap

Other Link： http://id.nii.ac.jp/1004/00001617/

Language：Japanese   Publisher：一般社団法人情報処理学会  

本稿では,構造学習手法に対する Boosting 手法を提案する.Boosting 学習手法は,学習事例の重みを変化させることで,与えられた弱学習器を使って,複数のモデルを学習し,それらを結合したモデルを構築し,判別を行なう.しかし,通常の Boosting 手法は,正例と負例が与えられる場合を想定しているため,明示的に負例が与えられない構造学習に適用するのは難しい.そこで,入力の正しい構造と,入力に対する最も高いスコアを持つ誤った構造を用いた Boosting 学習手法を提案する.また,Boosting の弱学習器となる構造学習手法において,Boosting によって決められる学習事例の重みを学習時の各事例の学習率としての利用する方法を提案する.本 Boosting 手法を,Semi-Markov Perceptron の学習手法に適用し,Noun Phrase Chunking,Text Chunking,Extended Named Entity Recognition で評価を行なった.その結果,本手法は,semi-Markov perceptron, semi-Markov CRF より高い精度を残せることが示せた.

CiNii Research

researchmap

Language：Japanese   Publisher：The Japanese Society for Artificial Intelligence  

DOI： 10.11517/jjsai.27.1_89

CiNii Research

researchmap

Language：Japanese  

CiNii Research

researchmap

Language：Japanese   Publisher：情報処理学会  

CiNii Research

researchmap

Language：Japanese   Publisher：Information Processing Society of Japan (IPSJ)  

In this paper, we propose an efficient stacking learning algorithm. For stacking learning, a training data for a stacking model construction is required apart from a training data for each model construction to be stacked. Our stacking learning algorithm acquires a training data for stacking by conducting cross-validation to a training data for each model construction. The cross-validation results are used as a training data for stacking. We evaluate our stacking method with IREX formal test data called GENERAL for evaluation and 'CRL data' for training. Our method improves accuracy to acquire a training data for stacking by conducting cross-validation with a larger number of subsets and attains F-measure of 85.83. This result is better than previous one in this literature under the same condition.

CiNii Research

researchmap

Language：Japanese   Publisher：一般社団法人 人工知能学会  

セマンティックWebにおいてはRDFによるメタデータをどう作成するかが課題である．本稿では，機械学習ベースの情報抽出技術による，メールや報告書といったテキストからのエンティティ及び関係情報の抽出手法と，その人脈情報検索への応用について述べる．

DOI： 10.11517/pjsai.jsai04.0.289.0

CiNii Research

researchmap

Language：Japanese  

CiNii Research

researchmap

Language：Japanese   Publisher：電子情報通信学会  

CiNii Research

researchmap

Publisher：The Japanese Society for Artificial Intelligence  

DOI： 10.11517/pjsai.jsai01.0.8.0

CiNii Research

researchmap

Applicant：富士通株式会社

Application no：特願2018-102745  Date applied：2018.5

Announcement no：特開2019-207566  Date announced：2019.12

Patent/Registration no：特許第7056381号  Date registered：2022.4 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2015-238064  Date applied：2015.12

Announcement no：特開2017-102871  Date announced：2017.6

Patent/Registration no：特許第6597250号  Date registered：2019.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2015-030107  Date applied：2015.2

Announcement no：特開2015-099608  Date announced：2015.5

Patent/Registration no：特許第6135692号  Date registered：2017.5 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2014-241717  Date applied：2014.11

Announcement no：特開2016-103192  Date announced：2016.6

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2013-194168  Date applied：2013.9

Announcement no：特開2015-060432  Date announced：2015.3

Patent/Registration no：特許第6307822号  Date registered：2018.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2013-153939  Date applied：2013.7

Announcement no：特開2015-026135  Date announced：2015.2

Patent/Registration no：特許第6136702号  Date registered：2017.5 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2013-136647  Date applied：2013.6

Announcement no：特開2015-011535  Date announced：2015.1

Patent/Registration no：特許第6127778号  Date registered：2017.4 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2013-111378  Date applied：2013.5

Announcement no：特開2013-218717  Date announced：2013.10

Patent/Registration no：特許第5917440号  Date registered：2016.4 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2012-277491  Date applied：2012.12

Announcement no：特開2014-120140  Date announced：2014.6

Patent/Registration no：特許第6015417号  Date registered：2016.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2012-275336  Date applied：2012.12

Announcement no：特開2014-120016  Date announced：2014.6

Patent/Registration no：特許第6015414号  Date registered：2016.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2012-269846  Date applied：2012.12

Announcement no：特開2013-069330  Date announced：2013.4

Patent/Registration no：特許第5644847号  Date registered：2014.11 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2011-284536  Date applied：2011.12

Announcement no：特開2013-134625  Date announced：2013.7

Patent/Registration no：特許第5776539号  Date registered：2015.7 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2011-093856  Date applied：2011.4

Announcement no：特開2011-159321  Date announced：2011.8

Patent/Registration no：特許第4804591号  Date registered：2011.8 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2011-067592  Date applied：2011.3

Announcement no：特開2011-138546  Date announced：2011.7

Patent/Registration no：特許第5614351号  Date registered：2014.9 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2010-272940  Date applied：2010.12

Announcement no：特開2012-123560  Date announced：2012.6

Patent/Registration no：特許第5750876号  Date registered：2015.5 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2010-270601  Date applied：2010.12

Announcement no：特開2012-118930  Date announced：2012.6

Patent/Registration no：特許第5703722号  Date registered：2015.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2010-149496  Date applied：2010.6

Announcement no：特開2012-014363  Date announced：2012.1

Patent/Registration no：特許第5482512号  Date registered：2014.2 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2010-003260  Date applied：2010.1

Announcement no：特開2011-141838  Date announced：2011.7

Patent/Registration no：特許第5381728号  Date registered：2013.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-296732  Date applied：2009.12

Announcement no：特開2011-138248  Date announced：2011.7

Patent/Registration no：特許第5493845号  Date registered：2014.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-269497  Date applied：2009.11

Announcement no：特開2011-113333  Date announced：2011.6

Patent/Registration no：特許第5445071号  Date registered：2014.1 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-100574  Date applied：2009.4

Announcement no：特開2010-250642  Date announced：2010.11

Patent/Registration no：特許第5458640号  Date registered：2014.1 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2011-504649  Date applied：2009.3

Patent/Registration no：特許第5110201号  Date registered：2012.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-042098  Date applied：2009.2

Announcement no：特開2010-198288  Date announced：2010.9

Patent/Registration no：特許第5245908号  Date registered：2013.4 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2008-317790  Date applied：2008.12

Announcement no：特開2010-140373  Date announced：2010.6

Patent/Registration no：特許第5396845号  Date registered：2013.11 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2008-232784  Date applied：2008.9

Announcement no：特開2010-067011  Date announced：2010.3

Patent/Registration no：特許第5163379号  Date registered：2012.12 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2008-193068  Date applied：2008.7

Announcement no：特開2010-033214  Date announced：2010.2

Patent/Registration no：特許第5206197号  Date registered：2013.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2008-193067  Date applied：2008.7

Announcement no：特開2010-033213  Date announced：2010.2

Patent/Registration no：特許第5206196号  Date registered：2013.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2008-169415  Date applied：2008.6

Announcement no：特開2010-009414  Date announced：2010.1

Patent/Registration no：特許第5374938号  Date registered：2013.10 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-520230  Date applied：2007.6

Patent/Registration no：特許第4992973号  Date registered：2012.5 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2009-515059  Date applied：2007.5

Patent/Registration no：特許第4957796号  Date registered：2012.3 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2007-035434  Date applied：2007.2

Announcement no：特開2008-198132  Date announced：2008.8

Patent/Registration no：特許第5245255号  Date registered：2013.4 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2006-182251  Date applied：2006.6

Announcement no：特開2008-009918  Date announced：2008.1

Patent/Registration no：特許第4861078号  Date registered：2011.11 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2006-069048  Date applied：2006.3

Announcement no：特開2007-249355  Date announced：2007.9

Patent/Registration no：特許第4753755号  Date registered：2011.6 

J-GLOBAL

researchmap

Applicant：富士通株式会社

Application no：特願2005-009322  Date applied：2005.1

Announcement no：特開2006-004399  Date announced：2006.1

Patent/Registration no：特許第4347226号  Date registered：2009.7 

J-GLOBAL

researchmap