Daichi MOCHIHASHI
Associate Professor, Intelligent Information Processing group, Department of Statistical Modeling
Phone: +81-50-5533-8569
E-mail: daichi
Personal
Homepage:		 http://www.ism.ac.jp/~daichi/
Date of Birth: July, 1973
Education: B.S. in Science, College of Arts and Sciences, The University of Tokyo, 1998.
Ph.D. in Science, Graduate School of Information Sciences, Nara Institute of Science and Technology, 2005.
Degree: Doctor of Science, Nara Institute of Science and Technology, 2005. Title of Doctoral Thesis: Distributional approaches to natural language processing.
Employment: 2003-2005 Researcher, ATR Spoken Language Communication Research Laboratories, Japan
2007-2010 Research Associate, NTT Communication Science Laboratories, Japan
2010-2011 Senior Research Associate, NTT Communication Science Laboratories, Japan
2011- Associate Professor, The Institute of Statistical Mathematics
Research
Fields:		 Statistical Natural Language Processing, Bayesian Machine Learning
Research
Themes:		 Nonparametric Bayesian methods, Latent variable models, Large scale Bayesian inference

Selected Papers
(1) S. Watanabe, D. Mochihashi, T. Hori, A. Nakamura (2011): Gibbs Sampling Based Multi-scale Mixture Model for Speaker Clustering. ICASSP 2011, to appear.
(2) Y. Ohishi, H. Kameoka, D. Mochihashi, H. Nagano (2010): Statistical Modeling of F0 Dynamics in Singing Voices Based on Gaussian Processes with Multiple Oscillation Bases. INTERSPEECH 2010, 2598-2601.
(3) T. Iwata, D. Mochihashi and H. Sawada (2010): Learning Common Grammar from Multilingual Corpus. ACL 2010, 184-188.
(4) D. Mochihashi, T. Yamada, N. Ueda (2009): Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling. ACL 2009, 100-108.
(5) M. Shimbo, T. Ito, D. Mochihashi, Y. Matsumoto (2009): On the Properties of von Neumann Kernels for Link Analysis. Machine Learning, 75, 37-67.
(6) D. Mochihashi, E. Sumita (2008): The Infinite Markov Model. Advances in Neural Information Processing Systems 20 (NIPS 2007), 1017-1024.
(7) D. Mochihashi, E. Sumita (2007): Variable n-gram language modeling based on Hierarchical Pitman-Yor processes. Journal of Information Processing Society of Japan, 48(12), 4023-4032. (in Japanese)
(8) T. Ito, J. Shimbo, D. Mochihashi, Y. Matsumoto (2007): Kernel Citation Analysis with Communities. IEICE Transactions on Information and Systems J90-D(2), 233-244. (in Japanese)
(9) T. Ito, M. Shimbo, D. Mochihashi, Y. Matsumoto (2006): Exploring Multiple Communities with Kernel-Based Link Analysis. ECML/PKDD 2006, 246-253.
(10) D. Mochihashi, Y. Matsumoto (2006): Context as Filtering. Advances in Neural Information Processing Systems 18 (NIPS 2005), 907-914.
(11) D. Mochihashi, G. Kikui, K. Kita (2005): Learning an Optimal Distance Metric in the Linguistic Vector Space. IEICE Transactions on Information and Systems, J88-D-II(4), 747-756. (in Japanese)
(12) D. Mochihashi, G. Kikui, K. Kita (2004): Learning Nonstructural Distance Metric by Minimum Cluster Distortions. EMNLP 2004, 341-348.

Membership of Academic Societies
Association of Computational Linguistics, Statistical Society of Japan, Information Processing Society of Japan, Institute of Electronics, Information and Communication Engineers (IEICE)

Professional Services
2008- : Senior committee, Information-based Induction Sciences and Machine Learning (IBISML) of Japan
Reviewed for NIPS, ICML, ACL, EMNLP, JMLR, TKDE, (in Japanese) IPSJ, IEICE, JSIAM

HOME