CURRICULUM VITAE

Yutaka Sasaki


Affiliation
Professor
Department of Advanced Science and Technology
Faculty of Engineering
Toyota Technological Institute
Adjoint Professor
Toyota Technological Institute at Chicago (June 2010-)
Part-time Lecture
Nagoya University (April 2010-March 2011)


Postal address
Toyota Technological Institute
2-12-1 Hisakata, Tempaku-ku
Nagoya, 468-8511, Japan

Email address

Education
Doctor of Philosophy in Engineering September 2000
University of Tsukuba, Japan
Master's Degree, Engineering March 1988
Master Program in Science and Engineering
University of Tsukuba, Japan
Bachelor's Degree, Engineering March 1986
College of Information Sciences
University of Tsukuba, Japan

Academic and research experiences
August 2013
Visiting Professor, University of Lyon 1, France.
November 2009 - present
Professor, Toyota Technological Institute, Japan
June 2010 - present
Adjunct Professor, Toyota Technological Institute at Chicago
April 2010 - March 2011
Part-time Lecturer, Nagoya University
October 2006 - November 2009
Research Fellow, School of Computer Science, University of Manchester, UK
August-September 2006
Research Fellow, School of Informatics, University of Manchester, UK
May-June 2006
Head of Department of Knowledge Processing, Knowledge Science Laboratories and Head of Department of Spoken Language Processing, Spoken Language Communication Research Laboratories, Advanced Telecommunications Research Institute International (ATR), Japan
April 2006
Head of Department of Knowledge Processing, Media Science Laboratories and Head of Department of Spoken Language Processing, Spoken Language Communication Research Laboratories, Advanced Telecommunications Research Institute International (ATR), Japan
April 2005 - March 2006
Head of Department of Natural Language Processing, Spoken Language Communication Research Laboratories, Advanced Telecommunications Research Institute International (ATR), Japan
July 2004 - March 2005
Head of Department of Natural Language Processing, Spoken Language Translation Research Laboratories, Advanced Telecommunications Research Institute International (ATR), Japan
Fall 2005
Part-Time Lecturer, Doshisha University, Shiga, Japan
Served as a lecturer for a course of Linear Algebra II; As an instructor, was fully responsible for development of curricula, design and presentation of lecture and exercise materials, and evaluation of about 100 undergraduate students.
June 2004
Chief Researcher, Department of Natural Language Processing, Spoken Language Translation Research Laboratories, ATR, Japan
March 1994 - May 2004
NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation (NTT), Japan
Fall 2000 and Fall 2001
Part-Time Lecturer, Mie University, Mie, Japan
Served as a lecturer for a course of Mathematical Logic; As an instructor, was fully responsible for development of curricula, design and presentation of lecture and exercise materials, and evaluation of about 75 undergraduate students.

July 1991 - February 1994
NTT Network Information System Laboratories, NTT, Japan
April 1988 - June 1991
NTT Communications and Information Processing Laboratories, NTT, Japan
September 1995 - September 1996
Visiting Researcher at Simon Fraser University, BC, Canada

Service to profession:
2016-2017 Program Committee Co-Chair, First International Workshop on Symbolic-Neural Learning
2014-2015 Program Committee Member, 21st Annual Meeting of the Association for Natural Language Processing
2014-2015 Advisory Board member, Project NEXT
2013 Local Committee Member, 19th Annual Meeting of the Association for Natural Language Processing
2013- Advisory Board member, European project BioASQ
2011- Editorial Board member, Journal of Natural Language Processing
2011 Program Committee Member, 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-2011)
2010 Program Committee Member, 4th International Symposium on Semantic Mining in Biomedicine (SMBM)
2009-2010 Scientific Committee Member, 7th Edition of the Language Resources and Evaluation Conference (LREC-2010)
2008-2009 Program Committee Member, 47th Annual Meeting of the Association for Computational Linguistics (ACL-2009)
2008-2009 Program Committee Member, The Fourth International Conference on Digital Telecommunications (ICDT-09)
2008 Program Committee Member, 2nd International ACM Workshop on Improving Non-English Web Searching (iNEWS-2008)
2007-2008 Scientific Committee Member, 6th Edition of the Language Resources and Evaluation Conference (LREC-2008)
2007-2008 Program Committee Member, 46th Annual Meeting of the Association for Computational Linguistics (ACL-2008) ,
2006-2007 Program Committee Member, 8th Conference on Large-Scale Semantic Access to Content (Text, Image, Video and Sound) (RIAO-2007)
2006-2007 Cco-organizer, NTCIR-6 Cross-Lingual Question Answering
2005 Program Committee Member, 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005)
2004-2005 Co-organizer, NTCIR-5 Cross-Lingual Question Answering
2004 NTCIR TALIP Recommendation Committee Member
2003-2005 Steering Committee Member, Special Interest Group on Natural Language Processing (SIGNL), Information Processing Society of Japan (IPSJ)
2003 Workshop co-chair, ACL 2003 Workshop on Multilingual Summarization and Question Answering (with Abraham Ittycheriah, Chin-Yew Lin, Tsuneaki Kato)
2001-2003 Program Committee member, NTCIR Question Answering Challenge
2002 Program Committee member, IEICE Symposium on Text Processing for Information Access

Reviewer for:
Sixth International Conference on Representation Learning (ICRL-2018)
Thirty-first Annual Conference on Neural Information Processing Systems (NIPS-2017)
Thirtht Annual Conference on Neural Information Processing Systems (NIPS-2016)
Journal of Biomedical Semantics
2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-2011)
BMC Bioinformatics
Artificial Intelligence in Medicine
Journal of Biomedical Informatics
7th edition of the Language Resources and Evaluation Conference (LREC-2010)
Integrated Computer-Aided Engineering
2nd International ACM Workshop on Improving Non-English Web Searching (iNEWS-2008)
6th edition of the Language Resources and Evaluation Conference (LREC-2008)
18th International Congress of Linguists (ICL-2008)
46th Annual Meeting of the Association for Computational Linguistics (ACL-2008)
ETRI Journal
2nd International Symposium on Languages in Biology and Medicine (LBM-2007)
43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005)
42nd Annual Meeting of the Association for Computational Linguistics (ACL-2004)
19th International Conference on Computation Linguistics (Coling-2002)
ACM Transactions on Asian Language Information Processing (TALIP)
Journal of Japanese Society for Artificial Intelligence (JSAI)
Journal of Information Processing Society of Japan (IPSJ)
Transactions of the Institute of Electronics, Information and Communication Engineers (IEICE)
Journal of Natural Language Processing

Professional memberships
Association for Computational Linguistics (ACL)
Japanese Society for Artificial Intelligence
Association for Natural Language Processing, Japan
Information Processing Society of Japan

Awards and honors
1991 Conference Paper Award, Annual Conference of Japanese Society of Artificial Intelligence (with Toru Ishida and Yoshimi Fukuhara)

Interviews by mass media
Mar. 9, 2005 Natural Language Processing, Nikkei BP, Japan
Dec.11, 2002 Question Answering System, Yomiuri Shimbun (Osaka), Japan
Jan. 7, 2002 Question Answering System, TV News Program "News 10",
NHK (Nippon Hoso Kyokai), Japan.
Dec. 1, 2001 Question Answering System, Nikkei COMPUTER, Nikkei BP, Japan
2001 Question Answering System, Asahi Shimbun (Kyoto), Japan

Research interests
Hierarchical Classification
Text Classification in a lot of practical areas requres classification into not only a flat multiple classes (i.e. categories) but also huge classess hierarchically structured. Typical hierarchical text classification application is classification of medical/clinical documents into ICD-10 codes or MeSH terms. We have participated in PASCAL LSHTC3 Challenge 2012. Fortunately, our system was one of the top 3 systems in the Wikipedia Medium subtask. Our hierarchical classification system, named Eze, has been released.
Fast Machine Learning Algorithms
Taking a machile learning approach to large-scale hierarchical text classification means "Big Data" Challenge in the machine learning context. Now a days, we have very fast SVM algorithms but when we need to train millions of models linked to a large-scale, real world class hierarchy, we need much more faster, but still high-performing, machine learning algorithms. We are interested in a variant of SGD SVM algorithm accelerated by massively parallel processors, such as CUDA GPGPUs and Hadoop clusters.
Deep Learning
We are now applying deep neural networks to natural language processing tasks. We developed image explanation selection methods based on the neural image explanation generation. We also applying deep learning to summarization, information extraction, langauge modelling, and opinion mining.
Question Answering
Question-Answering involves the extraction of an answer to a question from a large-scale document corpus. For instance, if a QA system is given the question ``Who is President of the USA?'', it should answer ``Barack Obama''. (c.f. IEICE Journal, Coling-02, ACL-03, NIPS-03 papers) I led a development of a Japanese QA System, SAIQA, since 2000. I contributed to studies on applying Statistical Learning Method, such as Support Vector Machines, Maximum Entropy Models, and Graph Kernels, to automatically construct QA systems from QA corpus. As a new direction of QA, Cross-Lingual QA (CLQA) is starting to attract researchers. I am an organizer of an international evaluation workshop, NTCIR-5 CLQA and NTCIR-6 CLQA.(c.f. my ACL-05 paper) Another research interests in QA related areas include automatic solvers for ESL tests (such as TOEIC and TOEFL). Recently, we ahieved good results in BioASK challenges.
Traffic and Machining Knowledge Base
We are now constructing a knowledge base in the car driving domain which will be installing the autonomous vehicles in the future. We also constructing ontologies for the machining domain.
Learning of information extraction (IE) rules
Research on generating information extraction rules from examples using typed-capable inductive logic programming techniques. (c.f. AAAI Workshop-99, Coling-00 papers) We also applied IE to biomedical documents. (c.f., bioNLP-09 workshop paper, Coling-2009 paper, Computational Intelligence Journal paper.)
Learning of typed logic programs from examples
Research on efficiently learning typed (or sorted) logic programs by treating type hierarchy as special background knowledge. (c.f. Our IJCAI-97, PADD-98, ALT-99, ECML-01 papers)
Supervised/Unsupervised learning in bioinformatics (past research)
BOOTStrep (Bootstrapping Of Ontologies and Terminologies STrategic REsearch Project) is funded in the EC's 6th Framework Programme. The project will pull together already existing biological fact databases as well as various terminological repositories and implement a text analysis system which continuously increases their coverage by analysing biological documents. My research interest in this project was to apply supervised/unsupervised learning techniques to biological documents. We participated in the BioNLP-09 shared task and i2b2-2010 NLP Challege.
Speech-to-Speech Translation (past research)
Development of a speech translation system to deal with all of these features. The mission of my department is to create machine translation engines suitable for speech-to-speech translation.
Analogy by Explanation Based Generalization (EBL) (past research)
Research on constructing knowledge structure in an unknown domain by converting knowledge in a known domain. Analogy is computed based on logical structure and relations among ground literals. It does not use similarity at all.
Rule-based Intelligent Systems (past research)
Research on separating control knowledge from a traditional rule base. This is achieved by describing meta-control knowledge which controls procedural execution of truly declarative rules. It was evaluated on an intelligent CAI system. (c.f. Our IEEE CAIA-91 paper and IEEE TKDE paper)

Dissertation research

Hierarchically Sorted Inductive Logic Programming and Its Application to Information Extraction
Committee: Tetsuo Ida (chair), Shigeru Igarashi, Jiro Tanaka, Middeldorp, Masahiko Sato
This research specializes in the learning of typed logic programs from examples and an application of the learning method to the generation of information extraction rules.

Selected publications
Journals:
[1] Lihua Zhao, Ryutaro Ichise Zheng Liu, Seiichi Mita, and Yutaka Sasaki, Ontology-based Driving Decision Making: A Feasibility Study at Uncontrolled Intersections, IEICE Transactions on Information and Systems, Vol. E100.D, No. 7, pp. 1425-1439, 2017. (pdf)
[2] Paul Thompson , John McNaught , Simonetta Montemagni , Nicoletta Calzolari , Riccardo del Gratta , Vivian Lee , Simone Marchi , Monica Monachini , Piotr Pezik , Valeria Quochi , C.j. Rupp , Yutaka Sasaki , Giulia Venturi , Dietrich Rebholz-Schuhmann and Sophia Ananiadou, The BioLexicon: a large-scale terminological resource for biomedical text mining BMC Bioinformatics, 12:397, 2011
[3] Yutaka Sasaki, Xinglong Wang, and Sophia Ananiadou, Extracting Secondary Bio-Event Arguments with Extraction Constraints, Computational Intelligence, Wiley-Blackwell, Nov. 2011. (in print)
[4] Sophia Ananiadou, Paul Thompson, James Thomas, Tingting Mu, Sandy Oliver, Mark Rickinson, Yutaka Sasaki, Davy Weissenbacher, and John McNaught, Supporting the education evidence portal via text mining, Philosophical Transactions of the Royal Society A, Royal Society, Vol. 368, No. 1925, pp. 3829-3844, 2010. (pdf)
[5] Yutaka Sasaki, John McNaught, and Sophia Ananiadou, The Value of an In-Domain Lexicon in Genomics QA, Journal of Bioinformatics and Computational Biology (JBCB), Imperial College Press, pp. 147-161, 2010.
[6]Yutaka Sasaki, Brian Rea, and Sophia Ananiadou, Clinical Text Classification under the Open and Closed Topic Assumptions, International Journal on Data Mining and Bioinformatics (IJDMB), Vol. 3, No. 3, pp. 299-313, Inderscience Publishers, 2009. (pdf)
[7] Yutaka Sasaki, Yoshimasa Tsuruoka, John McNaught, and Sophia Ananiadou, How to make the most of NE dictionaries in statistical NER, BMC Bioinformatics, 9(Suppl 11):S5, 2008. (html)
[8] Young-Sook Hwang, Andrew Finch, and Yutaka Sasaki, Improving Statistical Machine Translation Using Shallow Linguistic Knowledge, Computer Speech and Language, Elsevier, pp. 350-372, 2007. (pdf)
[9] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, Hierarchical Directed Acyclic Graph Kernel, Systems and Computers in Japan, 37(10): 58-68, 2006.(pdf)
[10] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, Hierarchical Directed Acyclic Graph Kernel, IEICE Trans, Vol. J88-DII, No. 2, pp. 230-240, 2005. (in Japanese)
[11] Yutaka Sasaki, Hideki Isozaki, Jun Suzuki, Kouji Kokuryou, Tsutomu Hirao, Hideto Kazawa, and Eisaku Maeda, SAIQA-II: A Trainable Japanese QA System with SVM, IPSJ Journal, Vol. 45, NO. 2, pp. 635-646, 2004. (in Japanese)
[12] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, Question Type Classification Using Word Attribute N-gram and Statistical Machine Learning, IPSJ Journal, Vol. 14, No. 11, pp. 2839-2853, 2003. (in Japanese)
[13] Yutaka Sasaki, Question Answering as Abduction: A Feasibility Study at NTCIR QAC1, IEICE Trans. Inf. & Syst., Special Issue on Text Processing for Information Access, Vol. E86-D, No. 9, pp. 1669-1676, 2003. (pdf)
[14] Tsutomu Hirao, Kazuhiro Takeuchi, Hideki Isozaki, Yutaka Sasaki, and Eisaku Maeda, SVM-Based Multi-Document Summarization Integrating Sentence Extraction with Bunsetsu Elimination, IEICE Trans. Inf. & Syst., Special Issue on Text Processing for Information Access, Vol. E86-D, No. 9, pp. 1702-1709, 2003.(pdf)
[15] Tsutomu Hirao, Yutaka Sasaki, and Hideki Isozaki, Question-Biased Text Summarization and Its Evaluation, IPSJ Journal, Vol.42, No.9, pp.2259-2269, 2001. (in Japanese)
[16] Yutaka Sasaki, Learning Typed Logic Programs from Positives, Journal of Japanese Society for Artificial Intelligence (JSAI), Vol. 15, No. 1, pp. 147-154, 2000. (in Japanese)
[17] Megumi Ishii, Yutaka Sasaki and Shigeo Kaneda, A Constraint-Satisfaction Approach to Clerical Work, IEEE Intelligent Systems, Vol. 15, No. 1, pp. 64-72, 2000. (abstract)
[18] Yutaka Sasaki, On the Necessity of Special Mechanisms for Handling Type in Inductive Logic Programming, IEICE Trans. Inf. & Syst., Vol. E82-D, No. 10, pp. 1401-1408, 1999.(pdf)
[19] Keiichi Hirota, Yutaka Sasaki, and Tsuneaki Kato, Ontology-Driven Information Extraction, Journal of Japanese Society for Artificial Intelligence, Vol. 14, No. 6, pp. 1010-1018, 1999. (in Japanese)
[20] Toru Ishida, Yutaka Sasaki and Keiko Nakata and Yoshimi Fukuhara, A Meta-Level Control Architecture for Production Systems, IEEE Transaction on Data and Knowledge Engineering (TKDE), Vol. 7, No. 1, pp. 44-52, 1995.(abstract)
Refereed conference papers:
[1] Mohammad Golam Sohrab, Toru Nakata, Makoto Miwa, Yutaka Sasaki, edge2vec: Edge Representations for Large-Scale Scalable Hierarchical Learning CICLING-2-17, 2017.
[2] Josuke Yamane, Tomoya Takatani, Hitoshi Yamada, Makoto Miwa and Yutaka Sasaki, Distributional Hypernym Generation by Jointly Learning Clusters and Projections, 26th International Conference on Computational Linguistics (COLING 2016), Osaka, Japan, December, 2016.
[3] Masataka Ono, Makoto Miwa, Yutaka Sasaki, Word Embedding-based Antonym Detection using Thesauri and Distributional Information, NAACL/HLT-2015, 2015.
[4] Mohammad Golam Sohrab, Makoto Miwa, Yutaka Sasaki, Centroid-Means-Embedding: An Approach to Infusing Word Embeddings into Features for Text Classification, The 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2015.
[5] Lihua Zhao, Ryutaro Ichise, Seiichi Mita, Yutaka Sasaki, An Ontology-Based Intelligent Speed Adaptation System for Autonomous Cars, The 4th Joint International Semantic Technology Conference (JIST2014), 2014;
[6] Makoto Miwa, Yutaka Sasaki, Modeling Joint Entity and Relation Extraction with Table Representation, in Proc. of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), Doha, Qatar, 2014.
[7] Davy Weissenbacher and Yutaka Sasaki, Which Factors Contributes to Resolving Coreference Chains with Bayesian Networks?, In Proc. of Computational Linguistics and Intelligent Text Processing (CICLing-2013), Samos, Greece, March 2013.
[8] Chikashi Nobata, Yutaka Sasaki, Naoaki Okazaki, C.J. Rupp, Junichi Tsujii, and Sophia Ananiadou, Semantic Search on Digital Document Repositories based on Text Mining Results, International Conferences on Digital Libraries and the Semantic Web 2009 (ICSD2009), Trento, 8-11, September, 2009.
[9] Giuila Venturi, Simonetta Montemagni, Simone Marchi, Yutaka Sasaki, Paul Thompson, John McNaught, and Sophia Ananiadou, Bootstrapping a Verb Lexicon for Biomedical Information Extraction. In Proceedings of Computational Linguistics and Intelligent Text Processing (CICLing-2009), Mexico, March 2009. (pdf)
[10] Yutaka Sasaki, Paul Thompson, Philip Cotter, John McNaught, and Sophia Ananiadou, Event Frame Extraction Based on a Gene Regulation Corpus, In Proc. of the 22nd International Conference on Computational Linguistics (Coling-2008), 18-22 August 2008, Manchester, pp. 761-768, 2008. (pdf)
[11] Yutaka Sasaki, Brian Rea, Sophia Ananiadou, Multi-Topic Aspects in Clinical Text Classification, IEEE International Conference on Bioinformatics and Biomedicine 2007 (IEEE BIBM-07), Silicon Valley, Nov. 2-7, pp.62-67, 2007.(pdf)
[12] Sophia Ananiadou, Brian Rea, Yutaka Sasaki, Rob Procter, and James Thomas, Supporting Systematic Reviews using Text Mining, in Proceedings of the Third International Conference on e-Social Science, Ann Arbor, Michigan, October 7-9, 2007. (pdf)
[13] Tohru Shimizu, Yutaka Ashikari, Toshiyuki Takezawa, Masahide Mizushima, Gen-ichiro Kikui, Yutaka Sasaki, Satoshi Nakamura, Developing Client-Server Speech Translation Platform, 7th International Conference on Mobile Data Management (MDM 2006), Nara, Japan, May 9-13, 2006. (pdf)
[14] Young-Sook Hwang, Taro Watanabe, and Yutaka Sasaki, Empirical Study of Utilizing Morph-Syntactic Information in SMT, 2nd International Joint Conference on Natural Language Processing (IJCNLP-2005), Jeju, 2005. (pdf)
[15] Yutaka Sasaki, Question Answering as Question-Biased Term Extraction: A New Approach toward Multilingual QA, 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005), pp. 215-222, Ann Arbor, 2005. (pdf)
[16] Young-Sook Hwang and Yutaka Sasaki, Context-dependent SMT Model Using Bilingual Verb-Noun Collocation, 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005), pp. 549-556, Ann Arbor, 2005. (pdf)
[17] Young-Sook Hwang, Kyonghee Paik, and Yutaka Sasaki, Bilingual Knowledge Extraction Using Chunk Alignment, 18th Pacific Asia Conference on Language, Information and Computation (PACLIC-18), pp. 127-137, Tokyo, 2004. (pdf)
[18] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, Kernels for Structured Natural Language Data, Eighteenth Annual Conference on Neural Information Processing Systems (NIPS-2003), Vancouver, 2003. (pdf)
[19] Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda, Hierarchical Directed Acyclic Graph Kernel: Methods for Structured Natural Language Data, 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003), Sapporo, pp. 32-39, 2003. (pdf)
[20] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, SVM Answer Selection for Open-Domain Question Answering, 19th International Conference on Computational Linguistics (Coling-2002), Taipei, pp.974-980, 2002. (pdf)
[21] Hassan Ait-Kaci and Yutaka Sasaki, An Axiomatic Approach to Feature Term Generalization, 12th European Conference on Machine Learning (ECML-2001), Freiburg, pp. 1-12, 2001. (pdf)
[22] Yutaka Sasaki and Yoshihiro Matsuo, Learning Semantic-Level Information Extraction Rules by Type-Oriented ILP, 18th International Conference on Computational Linguistics (Coling-2000), Saarbrucken, pp. 698-704, 2000. (pdf)
[23] Yutaka Sasaki, Induction of Logic Programs based on psi-terms, 10th International Conference on Algorithmic Learning Theory (ALT-99), Tokyo, Lecture Notes in Artificial Intelligence 1720, pp. 169-181, 1999. (pdf)
[24] Yutaka Sasaki, Learning of Information Extraction Rules using ILP -- Preliminary Report, 2nd International Conference on The Practical Application of Knowledge Discovery and Data Mining (PADD'98), London, pp. 195-205, 1998.
[25] Yutaka Sasaki and Masahiko Haruno, RHB+: A Type-Oriented ILP System Learning from Positive Data, 15th International Joint Conference on Artificail Intelligence (IJCAI-97), Nagoya, pp. 894-899, 1997.
[26] Megumi Ishii, Yutaka Sasaki and Shigeo Kaneda, Interactive Constraint Satisfaction for Office Systems, 10th IEEE Conference on Artificial Intelligence for Applications (CAIA-94), Austin, pp. 116-124, 1994.
[27] Toru Ishida, Yutaka Sasaki and Yoshimi Fukuhara, Use of Procedural Programming Language for Controlling Production Systems, 7th IEEE Conference on Artificial Intelligence Applications (CAIA-91), Miami, pp. 71-75, 1991.
Refereed Posters/Demos:
[1] Tomoki Tsujimura, Makoto Miwa, and Yutaka Sasaki, TTI-COIN at SemEval-2017 Task 10: Investigating Embeddings for End-to-End Relation Extraction from Scientific Papers, 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, Aug. 2017. (pdf)
[2] Takuma Yoneda, Kouki Mori, Makoto Miwa, Yutaka Sasaki, Bib2vec: Embedding-based Search System for Bibliographic Information, EACL-2017, 2017.
[3] Yutaka Sasaki, Paul Thompson, John McNaught, and Sophia Ananiadou, Three BioNLP Tools Powered by the BioLexicon, Proc of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL-09), 2009. (pfd)
[4] Dietrich Rebholz-Schuhmann, Piotr Pezik, Vivian Lee, Jung-Jae Kim, Riccardo del Gratta, Yutaka Sasaki, Jock McNaught, Simonetta Montemagni, Monica Monachini, Nicoletta Calzolari, Sophia Ananiadou, BioLexicon: Towards a Reference Terminological Resource in the Biomedical Domain, In Proc of the 16th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB-2008) (Poster), Toronto, Canada, 2008. (pdf)
[5] Splendiani, Andrea, Scott Piao, Yutaka Sasaki, Sophia Ananiadou, John McNaught, and Anita Burgun, Compositional Enrichment of Bio-Ontologies, the 11th Annual Bio-Ontologies Meeting (Poster), 20 July 2008, Toronto, Canada, 2008. (pdf)
[6] Sophia Ananiadou, Philip Cotter, Chikashi Nobata, Naoaki Okazaki, Brian Rea, Yutaka Sasaki, Yoshimasa Tsuruoka, Jun'ichi Tsujii, SemText: A Semantically Enriched Information Retrieval System for Biology, 8th International Conference on Systems Biology (ICSB-2007) (Poster), Long Beach, 1-6 Oct. 2007. (pdf)
[7] Chikashi Nobata, Philip Cotter, Naoaki Okazaki, Brian Rea, Yutaka Sasaki, Yoshimasa Tsuruoka, Jun-ichi Tsujii, and Sophia Ananiadou, Kleio: A Knowledge-Enriched Information Retrieval System for Biology, 31st Annual International ACM SIGIR Conference (SIGIR-2008) (Poster), 20-24 July 2008, Singapore, 2008. (to appear) (pdf)
[8] Yutaka Sasaki, Keiko Nakata, Toru Ishida and Yoshimi Fukuhara, Advantages of Meta-level Control Architectures in Maintaining Rule-Based Systems, 5th IEEE Conference on Tools with Artificial Intelligence (TAI-93) (Poster), Boston, pp. 495-496, 1993.
Refereed letters:
[1] Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda, Question Type Classification using Statistical Machine Learning, Forum on Information Technology (FIT2002), Information Technology Letters, pp. 89-90, 2002. (in Japanese)
Refereed workshop/symposium papers/notes:
[1] Masaki Asada, Makoto Miwa, Yutaka Sasaki, Extracting Drug-Drug Interactions with Attention CNNs, BioNLP Workshop, Vancouver, Aug. 4th, 2017. (pdf)
[2] Lihua Zhao, Ryutaro Ichise, Yutaka Sasaki, Zheng Liu, Tatsuya Yoshikawa, Fast Decision Making using Ontology-based Knowledge Base, 2016 IEEE Intelligent Vehicles Symposium, Gothenburg, Sweden, June 2016.
[3] Lihua Zhao, Ryutaro Ichise, Tatsuya Yoshikawa, Takeshi Naito, Toshiaki Kakinami, Yutaka Sasaki, Ontology-based Decision Making on Uncontrolled Intersections and Narrow Roads, 2015 IEEE Intelligent Vehicles Symposium, Seoul, 2015.
[4] Yutaka Sasaki and Davy Weissenbacher, TTI's System for the LSHTC3 Challenge, ECML/PKDD-2012 Discovery Challenge Workshop on Large-Scale Hierarchical Classification, Bristol, UK, September, 2012.
[5] Yutaka Sasaki, John McNaught, and Sophia Ananiadou, The Value of an In-Domain Lexicon in Genomics QA, 3rd International Symposium on Languages in Biology and Medicine (LBM-2009), Nov. 8-10, Jeju, 2009.
[6] Yutaka Sasaki, Paul Thompson, John McNaught, and Sophia Ananiadou, Biological Event Recognition with Textual Induction, 3rd International Symposium on Languages in Biology and Medicine (LBM-2009), Nov. 8-10, Jeju, 2009.
[7] Yutaka Sasaki, Simonetta Montemagni, Piotr Pezik, Dietrich Rebholz-Schuhmann, John McNaught, and Sophia Ananiadou, BioLexicon: A Lexical Resource for the Biology Domain, In Proc. of the Third International Symposium on Semantic Mining in Biomedicine (SMBM 2008), 2008. (pdf)
[8] Yutaka Sasaki, Yoshimasa Tsuruoka, John McNaught, and Sophia Ananiadou, How to Make the Most of NE Dictionaries in Statistical NER, ACL-2008 Workshop on Current Trends in Biomedical Natural Language Processing (BioNLP-08), Colombus, pp. 63-70, 2008. (pdf)
[9] Scott Piao, Sophia Ananiadou, Yoshimasa Tsuruoka, Yutaka Sasaki, and John McNaught, Mining Opinion Polarity Relations of Citations. In Proceedings of IWCS-7 (the 7th International Workshop on Computational Semantics) Tilburg, Netherland, pp. 366-371, 2007.
[10] Jun Suzuki, Hirotoshi Taira, Yutaka Sasaki, and Eisaku Maeda, Directed Acyclic Graph Kernel, ACL 2003 Workshop on Multilingual Summarization and Question Answering - Machine Learning and Beyond, Sapporo, 2003.(pdf)
[11] Tsutomu Hirao, Yutaka Sasaki, and Hideki Isozaki, An Extrinsic Evaluation for Question-Biased Text Summarization on QA Tasks, NAACL-2001 Workshop on Automatic Summarization, Pittsburgh. 61-68, 2001. (pdf)
[12] Yutaka Sasaki, Applying Type-Oriented ILP to IE Rule Generation, AAAI-99 Workshop on Machine Learning for Information Extraction, Orlando, pp. 43-47, 1999. (ps)
[13] Yutaka Sasaki and Masahiko Haruno, A Relational Learner with Hierarchical Background Knowledge, ECML95 Workshop on Knowledge Level Modeling and ML, 1995.
[14] Yutaka Sasaki, Masahiko Haruno, and Shigeo Kaneda, Grammar Rule Extension with Structured Background Knowledge of Paraphrases from Unparsable Sentences, Japanese Knowledge Acquisition for Knowledge-Based Systems Workshop (JKAW-94), Hatoyama, pp. 243-252, 1994.
[15] Yutaka Sasaki, Masahiko Haruno, and Shigeo Kaneda, Grammar Rule Revision by Rephrasing Unparsable Sentences, ECML-94 Workshop on theory revision and restructuring, workshop note, Catania, 1994.
Other publications:
[1] 佐々木 裕, 三輪 誠, 古谷 克司, 原田 博正, 寺本 一成, Markov Logic Network による機械加工因子間の確率推定, 第31回人工知能学会全国大会, 名古屋, 2017. (pdf)
[2] 浅田 真生 三輪 誠 佐々木 裕, アテンションCNNによる薬物間相互作用抽出, 第31回人工知能学会全国大会, 名古屋, 2017. (pdf)
[3] 水口 凱 高谷 智哉 山田 整 三輪 誠 佐々木 裕, LSTMを用いた句のベクトル表現学習, 第31回人工知能学会全国大会, 名古屋, 2017. (pdf)
[4] 森洸樹, 三輪誠, 佐々木裕:n-gram素性に対する注意機構を利用したニューラルネットによる単語穴埋め 第23回言語処理学会年次大会, P8-3, 2017.
[5] 高山隼矢, 三輪誠, 佐々木裕:交通オントロジーに基づく質問応答データセットの構築, 第23回言語処理学会年次大会, P8-3, 2017.
[6] 山口修平, 山根丈亮, 三輪誠, 佐々木裕:ラティス構造を学習するニューラル単語分割, 第23回言語処理学会年次大会, P8-3, 2017.
[7] 瀧川雅也, 三輪誠, 佐々木裕:線形化された構文情報を用いた生成型ニューラル文要約, 第23回言語処理学会年次大会, P8-3, 2017.
[8] 立林裕太朗, 藤田充洋, 古谷克司, 佐々木裕: GAによる構文木枝刈りを用いた単一文書要約, 第22回言語処理学会年次大会, P12-7, 2016.
[9] 増田和浩, 増田和浩, 寺本一成, 古谷克司, 佐々木裕: Trigger Wordと部分文字列を用いた機械加工用語の関係抽出, 第22回言語処理学会年次大会, P14-7, 京都, 2016.
[10] 高里盛良, 三輪誠, 佐々木裕, ニューラルキャプション生成モデルによる画像説明文の選択, 第22回言語処理学会年次大会, P4-4, 仙台, 2016.
[11] 外山洋太, 三輪誠, 佐々木裕, 文書・文間及びカテゴリ間の関係を考慮したレーティング予測, 第22回言語処理学会年次大会, P6-6, 仙台, 2016.
[12] Mohammad Golam Sohrab, Makoto Miwa, Yutaka Sasaki, Word Embeddings in Large-Scale Deep Architecture Learning, 第22回言語処理学会年次大会, B3-3, 仙台, 2016.
[13] 山根丈亮, 高谷智哉, 山田整, 三輪誠, 佐々木裕, 上位語・下位語の射影関係とそのクラスタの同時学習, 第22回言語処理学会年次大会, B3-4, 仙台, 2016.
[14] Lihua Zhao, Ryutaro Ichise, Seiichi Mita, Yutaka Sasaki, Ontologies for Advanced Driver Assistance Systems, セマンティックウェブとオントロジー研究会, 23th March, 2015. (pdf)
[15] 河辺一仁, 三輪誠, 佐々木裕, 交通オントロジーの半自動拡張のための交通用語認識, 第21回言語処理学会年次大会, P2-4, pp.134-138, 京都, 2015. (pdf)
[16] 牧瀬晃太, 三輪誠, 佐々木裕: 学習型質問応答における単語文脈ベクトルの効果の研究, 第21回言語処理学会年次大会, P2-12, pp.167-170, 京都, 2015. (pdf)
[17] 鈴木遼司, 三輪誠, 佐々木裕: 交通オントロジーを対象とした質問文のSPARQLクエリ変換, 第21回言語処理学会年次大会, P2-13, pp.171-174, 京都, 2015. (pdf)
[18] 佐々木裕, Mohammad Golam Sohrab, 三輪誠:DCASVMを用いた高性能な大規模階層的文書分類, 第21回言語処理学会年次大会, D3-4, pp.485-488, 京都, 2015. (pdf)
[19] 大竹翔馬, 三輪誠, 佐々木裕: 文のカテゴリと極性の度合いの推定を行う評判分析システムの研究, 第21回言語処理学会年次大会, P3-3, pp.521-524, 京都, 2015. (pdf)
[20] 小野正貴, 三輪誠, 佐々木裕: 辞書と文脈情報を用いた対義語モデルの学習, 第21回言語処理学会年次大会, C5-2, pp.756-759, 京都, 2015. (pdf)
[21] 森洸樹, 三輪誠, 佐々木裕: 語順と共起を考慮したニューラル言語モデルによる英文穴埋め, 第21回言語処理学会年次大会, C5-3, pp.760-763, 京都, 2015. (pdf)
[22] 藤谷宣典, 三輪誠, 佐々木裕:隠れ状態を用いたホテルレビューのレーティング予測, 第21回言語処理学会年次大会, C5-4, pp.764-767, 京都, 2015. (pdf)
[23] 立林裕太朗, 藤田充洋, 古谷克司, 佐々木裕: GAによる機械加工メモの自動要約に関する予備検討, 第21回言語処理学会年次大会, P3-18, pp.581-584, 京都, 2015. (pdf)
[24] 増田和浩, 寺本一成, 古谷克司, 佐々木裕: SVMを用いた機械加工文書からの直接的因果関係の抽出 (pp. 第21回言語処理学会年次大会, P4-12, pp.936-939, 京都, 2015. (pdf)
[25] 白石裕次郎, 佐々木裕:英語穴埋め問題の自動解法, 第20回言語処理学会年次大会, P2-8, pp.101-104, 札幌, 2014. (pdf)
[26] 佐藤敦美, 佐々木裕:英語読解問題の自動解法, 第20回言語処理学会年次大会, P2-9, pp.105-108, 札幌, 2014. (pdf)
[27] 佐々木裕, Mohammad Golam Sohrab: LSHTC4 のための TTI 文書分類システム, 第20回言語処理学会年次大会, C1-4, pp.336-339, 札幌, 2014. (pdf)
[28] 立林裕太朗, 藤田充洋, 古谷克司, 佐々木: 機械加工技術文書の自動要約, pp.638-641, 札幌, 2014. (pdf)
[29] 増田和浩, 寺本一成, 古谷克司, 佐々木裕: 械加工技術文書の自動要約, pp.74-77, 札幌, 2014. (pdf)
[30] 大場弘樹, 佐々木 裕:Self-Trainingを用いた電子カルテからの関係抽出, 第19回言語処理学会年次大会, Y1-3, pp.87-90, 名古屋, 2013. (pdf)
[31] 佐々木 裕, Davy Weissenbacher: LSHTC3データを対象にした大規模階層的文書分類, 第19回言語処理学会年次大会, D3-2, pp.224-227, 名古屋, 2013. (pdf)
[32] 小野正貴, David McAllester, 佐々木裕: 大規模文書分類のためのSGD SVMの高速化, 第19回言語処理学会年次大会, P2-12, pp.446-448, 名古屋, 2013. (pdf)
[33] 杉村皓太, 佐々木裕: 交通規則問題のための解答システムの構築, 第19回言語処理学会年次大会, P5-14, pp.790-793, 名古屋, 2013. (pdf)
[34] 佐々木 裕, 長谷川 雄: GPGPUによるSVM分類器の高速化, 第18回言語処理学会年次大会, F2-1, pp.513-516, 広島, 2012. (pdf)
[35] 佐々木 裕:GPGPUによる超並列処理の文書分類への適用, 第17回言語処理学会年次大会, C2-4, pp.484-487, 豊橋, 2011. (pdf)
[36] 石原 健太, 山本 幸也, Davy Weissenbacher, 佐々木 裕:電子カルテからの医療用語の抽出, P1-22, pp.244-247, 豊橋, 2011. (pdf)
[37] Yutaka Sasaki, Kenta Ishihara, Yukiya Yamamoto, Davy Weissenbacher, TTI's Systems for 2010 i2b2/VA Challenge, i2b2 Wrokshop 2010, Washington D.C., Nov. 2010.
[38]Satoshi Brian Rea, Davy Weissenbacher, Yutaka Sasaki, James Thomas, and Sophia Ananiadou, ASSIST: Education Evidence Portal, UK e-Science All Hands Meeting 2009, Oxford, 7-9 Dec. 2009.
[39]Satoshi Nakamura, Yutaka Sasaki, Gen-ichiro Kikui, Toru Shimizu, A Review of Speech-to-Speech Translation, The Journal of Information Science and Technology Association, Vol. 55, No. 8, 2005. (in Japanese)(pdf)
[40] Eiichiro Sumita, Yutaka Sasaki, and Seiichi Yamamoto, The Forefront of Evaluation Methods for Machine Translation Systems, IPSJ Magazine, Vol. 46, No. 5, pp. 552-557, 2005. (in Japanese)
[41] Satoshi Nakamura and Yutaka Sasaki, Toward Common Evaluation Frameworks for Speech Recognition and Speech Translation Technology, ASJ Journal, pp. 225-230, 2005. (in Japanese)
[42] Yutaka Sasaki, A Comprehensive Evaluation of MT and QA Technologies: The Aims of NTCIR CLQA, in Proc. of NLP-2005 Workshop, 2005. (in Japanese)
[43]Yutaka Sasaki, A Comprehensive Learning Approach to Trainable QA: Toward CLQA, IPSJ SIGNotes NL-163-17, pp. 123-130, 2004. (in Japanese)
[44]Chiori Hori, Takaaki Hori, Hajime Tsukada, Hideki Isozaki, Yutaka Sasaki and Eisaku Maeda, Spoken Interactive ODQA System: SPIQA, ACL-2003 Interactive Poster and Demonstration Session, 2003.
[45] Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda, Efficient Calculation for Similarity between Texts using Hierarchical Structure, IPSJ SIGNotes NL-154-15, pp. 101-108, 2003. (in Japanese) (pdf)
[46] Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda, Efficient Calculation for Simularity between Texts using Text Structures, In proc. of the 9th Annual Meeting of The Association for Natural Language Processing, pp. 509-512, 2003. (in Japanese)
[47] Takashi Honishi, Yutaka Sasaki, and Junji Tomita, Information Retrieval Technologies for Portal Services, NTT R&D, Vol. 52, No. 2, pp. 73-77, 2003. (in Japanese)
[48] Eisaku Maeda, Hideki Isozaki, Yutaka Sasaki, Hideto Kazawa, Tsutomu Hirao, Jun Suzuki, Question Answering System: SAIQA -- A "Learned Computer" That Answers Any Questions, NTT R&D, Vol. 52, No. 2, pp. 122-133, 2003. (in Japanese)
[49] Yutaka Sasaki, Hideki Isozaki, Koji Kokuryou, Tsutomu Hirao, and Eisaku Maeda, NTT's QA Systems for NTCIR QAC-1, working notes, NTCIR Workshop 3, Tokyo, 2002. (pdf)
[50] Tsutomu Hirao, Kazuhiro Takeuchi, Hideki Isozaki, Yutaka Sasaki, and Eisaku Maeda, NTT/NAIST's Text Summarization Systems for TSC-2, working notes, NTCIR Workshop 3, Tokyo, 2002. (pdf)
[51] Yutaka Sasaki, SAIQA-II: A Trainable Question Answering System, working notes, NTT-Stanford Workshop on Concept and Language Processing, September, 2002.
[52] Tsutomu Hirao, Yutaka Sasaki, Hideki Isozaki, and Eisaku Maeda, NTT's Text Summarization System for DUC-2002, Document Understanding Conference (DUC-2002), 2002. (ps)
[53] Yasushi Ogawa, Yutaka Sasaki, Shigeru Masuyama, Masaki Murata, and Masaharu Yoshioka, NTCIR from Participants' Viewpoints, Journal of JSAI, Vol. 17, No.3, pp. 306-311, 2002.
[54] Eisaku Maeda, Hideki Isozaki, and Yutaka Sasaki, Future Humanoids Swallowing Worldwide Libraries, NTT R&D, Vol. 50, No. 12, pp. 953-962, 2001. (in Japanese)
[55] Yutaka Sasaki, Hideki Isozaki, Hirotoshi Taira, Tsutomu Hirao, Hideto Kazawa, Jun Suzuki, Kouji Kokuryou, and Eisaku Maeda, SAIQA: A Japanese QA System based on a Large-Scale Corpus, FI64/NL145-12, IPSJ SIG notes, 2001. (in Japanese) (pdf)
[56] Yutaka Sasaki, Hideki Isozaki, Hirotoshi Taira, Keiichi Hirota, Hideto Kazawa, Tsutomu Hirao, Hiroyuki Nakajima, and Tsuneaki Kato, An Evaluation and Comparison of Japanese Question Answering Systems, Technical Report of IEICE, NLC-2000-24, pp. 17-24, 2000. (in Japanese)
[57]Keiichi Hirota, Yutaka Sasaki, and Tsuneaki Kato, Constructing Domain Ontologies from Documents, NL140-08, IPSJ SIG notes, 2000. (in Japanese) (pdf)
[58] Yutaka Sasaki, Japanese Named Entity Extraction by Finite State Transducers, Fifth Annual Meeting of the Association for Natural Language Processing, pp. 108-111, 1999. (in Japanese)
[59] Keiichi Hirota, Yutaka Sasaki, and Tsuneaki Kato, Design of Ontology-Driven Information Extraction, NL133-12, IPSJ SIG notes, 1999. (in Japanese) (pdf)
Japanese Patents:
[1] 特願平4-82981 (出願日:平成4年3月6日)佐々木 裕「類似説明生成システム」
[2] 特願平5-230051 (出願日:平成5年6月16日)金田 重郎, 佐々木 裕,石井 恵「学習型認識システム」
[3] 特願平6-247797 (出願日:平成6年10月13日)佐々木 裕「文法規則拡張システム」
[4] 特願平7-181768 (出願日:平成7年7月18日)佐々木 裕「学習方法および学習システム」
[5] 特願平7-85055 (平成7年4月11日) 佐々木 裕, 春野 雅彦「学習装置」
[6] 特願平7-178768 (出願日:平成7年7月14日)佐々木 裕, 島田 茂夫, 湯川 高志, 山崎 毅文, 阿部 明典, 森 啓, 太田 昌克, 牧野 俊朗「知識取引システム」
[7] 特願平11-6202 (出願日:平成11年1月13日)廣田 啓一, 佐々木 裕「情報抽出方法及び装置及び情報抽出プログラムを格納した記憶媒体」
[8] 特願平11-067563 (出願日:平成11年3月12日)佐々木 裕,廣田 啓一「情報列に対してタグ情報を付与するための方法および装置ならびに同方法が記録される記録媒体」
[9] 特願平2000-140478(出願日:平成12年5月12日)廣田 啓一,佐々木 裕「表構造領域からの情報抽出方法および装置と情報抽出プログラムを記録した記録媒体」
[10] 特願平2000-048267(出願日:平成12年2月24日)佐々木 裕,廣田 啓一,加藤 恒昭「有限状態変換器生成装置、有限状態変換器生成方法及び有限状態変換器生成プログラムを記録した記録媒体」
[11] 特願平2000-166963 (出願日:平成12年6月5日) 廣田 啓一,佐々木 裕,加藤 恒昭「分野用語辞書構築方法、分野用語辞書構築装置および分野用語辞書構築プログラムを記録した記録媒体」
[12] 特願2000-319998 (出願日:平成12年10月19日) 佐々木 裕,磯崎 秀樹,平 博順,廣田 啓一,賀沢 秀人, 平尾 努,中島 浩之,加藤 恒昭 「質問応答方法、質問応答システム及び質問応答プログラムを記録した 記録媒体」
[13] 特願2001-333031 (出願日:平成13年10月30日) 鈴木 潤,佐々木 裕,前田 英作 「解答抽出方法、装置、プログラム、および同プログラムを記録した記録媒体」
[14] 特願2002-169457 (出願日:平成14年6月11日) 佐々木 裕「記号列分割装置、記号列分割方法、記号列分割プログラム及びそのプログラムを記録した記録媒体」
[15] 特願2002-253853 (出願日:平成14年8月30日) 鈴木 潤、佐々木 裕、前田 英作「質問タイプ学習方法、学習装置、質問タイプ学習プログラム、同プログラムを記録した記録媒体、学習データを記録した記録媒体、学習データを用いた質問タイプ同定方法、装置、プログラム、および該プログラムを記録した記録媒体」
[16] 特願2002-246328 (出願日:平成14年8月27日)國領 弘治,佐々木 裕,前田 英作「時系列情報からの固有情報抽出方法および装置,並びに時系列情報からの固有情報抽出プログラムおよびそのプログラムを記録した記録媒体」
[17] 特願2002-291221(出願日:平成14年10月3日)佐々木 裕「質問応答方法、質問応答装置、質問応答プログラム及び記録媒体」
[18] 特願2016-035175(出願日:平成28年2月26日)佐々木 裕「自動質問解答方法、そのためのモデル作成方法、およびコンピュータプログラム」
[19] 特願2004-256505(出願日:平成16年9月3日)高谷智哉,山田整,佐々木 裕,三輪誠,山根丈亮「話題推定学習装置及び話題推定学習方法」
[20] 寺本 一成,桑野義正,原田博正,佐々木裕「知識モデル構築システム及び知識モデル構築方法」