Yuta Tsuboi

Bio.

Currently, I'm working at Preferred Networks, Inc.
I received my M.E. from Nara Institute of Science and Technology (NAIST) in 2002, and had been engaged in research on text mining at IBM Research from 2002 to 2016.
I received my D.E. from NAIST in 2009.
My research interests include natural language processing, machine learning, and data mining.
I am a member of Information Processing Society of Japan and Association for Natural Language Processing.

• Twitter: yuutat

Research Topics

• Natural Language Processing, Information Extraction, Machine Learing, Data Mining

Publications

Journal Papers

• Hiroshi Kajino, Yuta Tsuboi, Issei Sato and Hisashi Kashima. "Learning from Crowds and Experts", Journal of Japanese Society of Artificial Intelligence (in Japanese), Vol.28, No.3, pp.243-248, 2013.
• Shinsuke Mori, Graham Neubig, and Yuta Tsuboi. "A Pointwise Approach to Automatic Word Segmentation", IPSJ Journal (in Japanese), Vol. 52, No. 10, pp.2944-2952, 2011.
• Shohei Hido, Yuta Tsuboi, Hisashi Kashima, Masashi Sugiyama and Takafumi Kanamori. "Statistical Outlier Detection Using Direct Density Ratio Estimation", Knowledge and Information Systems, Vol. 26, No. 2, pp.309-336, 2010.
• Yuta Tsuboi, Hisashi Kashima, Shinsuke Mori, Hiroki Oda, and Yuji Matsumoto. "Training Conditional Random Fields Using Partial Annotations for Domain Adaptation of Japanese Word Segmentation"(PDF*1), IPSJ Journal (in Japanese), Vol. 50, No. 6, pp.1622-1635, 2009.
• Yuta Tsuboi, Hisashi Kashima, Shohei Hido, Steffen Bickel, and Masashi Sugiyama. "Direct Density Ratio Estimation for Large-scale Covariate Shift Adaptation"(PDF*1), Journal of Information Processing, Vol. 17, pp.138-155, 2009.
• Hisashi Kashima, Shoko Suzuki, Shohei Hido, Yuta Tsuboi, Toshihiro Takahashi, Tsuyoshi Ide, Rikiya Takahashi, and Akira Tajima. "A Semi-Supervised Learning Approach Using Spatio-Temporal Information for Indoor Location Estimation", IEEE Intelligent Systems, 2008
• Shoko Suzuki, Yuta Tsuboi, Hisashi Kashima, Shohei Hido, Toshihiro Takahashi, Tsuyoshi Ide, Rikiya Takahashi, and Akira Tajima. "Transferring the Learned Knowledge for Indoor Location Estimation by Nonlinear Dimension Reduction", IEEE Intelligent Systems, 2008

Publications in Refereed Conferences

• Motoki Sato, Hiroki Ouchi, and Yuta Tsuboi. "Addressee and Response Selection for Multilingual Conversation", Proceedings of International Conference on Computational Linguistics (COLING), 2018.
• Jun Hatori, Yuta Kikuchi, Sosuke Kobayashi, Kuniyuki Takahashi, Yuta Tsuboi, Yuya Unno, Wilson Ko, and Jethro Tan. Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions (Arxiv, Project page, Dataset), Proceedings of International Conference on Robotics and Automation (ICRA), 2018.
• Hiroki Ouchi and Yuta Tsuboi. "Addressee and Response Selection for Multi-Party Conversation" (Dataset/Codes), Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016.
• Yuta Tsuboi. "Neural Networks Leverage Corpus-wide Information for Part-of-speech Tagging" (poster pptx), Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
• Hiroshi Kanayama, Youngja Park, Yuta Tsuboi, and Dongmook Yi. "Learning from a Neighbor: Adapting a Japanese Parser for Korean Through Feature Transfer Learning", Proceedings of the EMNLP'2014 Workshop on Language Technology for Closely Related Languages and Language Variants (LT4CloseLang), 2014.
• Hiroshi Kajino, Yuta Tsuboi, and Hisashi Kashima. "Clustering Crowds", Proceedings of 27th AAAI Conference on Artificial Intelligence (AAAI), 2013.
• Hiroshi Kajino, Yuta Tsuboi, Issei Sato, and Hisashi Kashima. "Learning from Crowds and Experts", Proceedings of Human computation workshop (HCOMP), 2012.
• Hiroshi Kajino, Yuta Tsuboi, and Hisashi Kashima. "A Convex Formulation for Learning from Crowds", Proceedings of 26th AAAI Conference on Artificial Intelligence (AAAI), 2012.
• Yuta Tsuboi, Yuya Unno, Hisashi Kashima, and Naoaki Okazaki. "Fast Newton-CG Method for Batch Learning of Conditional Random Fields", Proceedings of 25th AAAI Conference on Artificial Intelligence (AAAI), 2011.
• Rudy Raymond, Yuta Tsuboi, Hisashi Kashima, and Issei Sato. "Proximity in Large Bipartite Graphs with Unsupervised Auxiliary Information", Proceedings of the Asian Conference on Machine Learning (ACML), 2010 (poster).
• Hisashi Kashima, Shohei Hido, Yuta Tsuboi, Akira Tajima, Takeshi Ueno, Naoki Shibata, Ichiro Sakata and Toshiya Watanabe. "Predictive Modeling of Patent Quality by Using Text Mining" (slides), Proceedings of 19th International Conference on Management of Technology (IAMOT), Cairo, Egypt, 2010.
• Shohei Hido, Yuta Tsuboi, Hisashi Kashima, Masashi Sugiyama and Takafumi Kanamori. "Inlier-based outlier detection via direct density ratio estimation"(slides), Proceedings of 8th IEEE International Conference on Data Mining (ICDM), 2008.
• Yuta Tsuboi and Hisashi Kashima. "A New Objective Function for Sequence Labeling"(slides), Proceedings of International Conference on Pattern Recognition (ICPR), 2008.
• Yuta Tsuboi, Hisashi Kashima, Shinsuke Mori, Hiroki Oda, and Yuji Matsumoto. "Training Conditional Random Fields Using Incomplete Annotations"(slides), Proceedings of 22nd International Conference on Computational Linguistics (COLING), 2008.
• Yuta Tsuboi, Hisashi Kashima, Shohei Hido, Steffen Bickel, and Masashi Sugiyama. "Direct density ratio estimation for large-scale covariate shift adaptation" (poster, and presentation slides), Proceedings of SIAM International Conference on Data Mining (SDM), 2008.
• Hisashi Kashima and Yuta Tsuboi. "Kernel-based Discriminative Learning Algorithms for Labeling Sequences, Trees and Graphs", Proceedings of 21st International Conference on Machine Learning (ICML), 2004.
• Kaoru Yamamoto, Taku Kudo, Yuta Tsuboi, and Yuji Matsumoto. "Learning sequence-to-sequence correspondences from parallel corpora via sequential pattern mining", Proceedings of the HLT-NAACL 2003 Workshop on Building and using parallel texts, 2003.

Publications in Non-refereed Conferences

• Hiroki Ouchi, Yuta Tsuboi. A Neural Response Selection Model for Multi-party Text Conversation, 22nd Annual Meeting of the Association of Natural Language Processing (in Japanese), 2016.
• Yuta Tsuboi. Deepen A Neural Part-of-Speech Tagger(slides), 21st Annual Meeting of the Association of Natural Language Processing (in Japanese), 2015.
• Yuta Tsuboi, Hiroshi Kanayama, Katsumasa Yoshikawa, Tetsuya Nasukawa, Akihiro Nakayama, Kei Sugano, John Richardson. "Transfer of dependency parser from rule-based system to learning-based system"(slides), Proceedings of 20th Annual Meeting of the Association of Natural Language Processing (in Japanese), 2014.
• Masaki Ohno, Yuta Tsuboi, Hiroshi Kanayama, and Katsumasa Yoshikawa. "IBM Team at NTCIR-10 RITE2: Textual Entailment Using Temporal Dimension Reduction", Proceedings of the 10th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 545-552, 2013.
• Yuta Tsuboi. "Avoiding the error propagation of deterministic analysis via imitation learning" (slides), Proceedings of 19th Annual Meeting of the Association of Natural Language Processing (in Japanese), 2013.
• Daisuke Takuma, Yuta Tsuboi, Koichi Takeda, Issei Yoshida, Takahide Nogayama, Ai Ishida, Noriko Inaoka and Yujiro Takai. "Indexing Event Sequences for Medical Record Analysis", Proceedings of the International Workshop on Pattern Recognition for Healthcare Analytics, 2012.
• Yuta Tsuboi, Hiroshi Kanayama, Masaki Ohno, and Yuya Unno. "Syntactic Difference Based Approach for NTCIR-9 RITE Task", Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 404-411, 2011.
  We achieve the best score in the Japanese MC and Entrace Exam subtasks.
• Yuta Tsuboi, Yuya Unno, Hisashi Kashima, and Naoaki Okazaki. "Newton-CG method for Batch Learning of Conditional Random Fields"(slides), Proceedings of 17th Annual Meeting of the Association of Natural Language Processing (in Japanese), 2011.
• Yuya Unno and Yuta Tsuboi. "A Domain-aware Input Assist Method"(slides), Proceedings of 17th Annual Meeting of the Association of Natural Language Processing (in Japanese), 2011.
• Rudy Raymond, Yuta Tsuboi, Tetsuya Nasukawa, and Yao-zhong Zhang. "Finding Cross-Lingual Related Words by Random Walk on Bipartite Graphs", Proceedings of 17th Annual Meeting of the Association of Natural Language Processing, 2011.
• Yuya Unno and Yuta Tsuboi. "A Fast Extraction Method of a Set of Comact Contexts for String Search Results" (slides), The 5th NLP Symposium for Young Researchers (YANS2010), No. 7 (in Japanese), 2010.
• Risa Nishiyama, Yuta Tsuboi, Yuya Unno and Hironori Takeuchi. "Feature-Rich Information Extraction for the Technical Trend-Map Creation", Proceedings of the 8th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, 2010.
  We achieve the best score in the Japanese Technical Trend-Map Creation subtask.
• Yuya Unno and Yuta Tsuboi. "Distance Metric Based on Dependency Marginal Probabilities", Proceedings of 16th Annual Meeting of the Association of Natural Language Processing (in Japanese), pp. 23-26, 2010.

Book Translations

• Ronen Feldman and James Sanger. "The Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data (Japanese edition)", Tokyo Denki University Press, 2010 (I mainly translated chapter 7 and 9).

Doctoral Dissertation

• Yuta Tsuboi. Domain Adaptation of Statistical Word Segmentation System, Graduate School of Information Science, Nara Institute of Science and Technology, 2009．

Awards

• ICRA Best Paper Award on Human-Robot Interaction (HRI), 2018
• JSAI Field Innovation Award (Gold) 2009, The Japanese Society for Artificial Intelligence (JSAI), 2010.
• IPSJ Best Paper Award 2009, Information Processing Society of Japan (IPSJ), 2010. (by Journal Paper)
• The winner in Task 1 and the second-runner up in Task 2, IEEE Data Mining Contest, IEEE, 2007.

Activities

• Councilor of Association of Natural Language Processing in Japan, April 2014 - March 2018
• Program Committee Member of Asian Conference on Machine Learning (ACML), 2010, 2011.
• Program Committee Member of International Conference on Computational Linguistics (COLING), 2010.
• Steering Committee Member of Information Processing Society of Japan (IPSJ) SIG-NL, 2007-2010.