RIKEN Center for Advanced Intelligence Project Tourism Information Analytics Team

Team Leader: Satoshi Nakamura (D.Eng.)

Japanese Page

Research Summary

Japan’s Inbound tourism is drastically growing. The demands from tourists have been becoming stronger and more diverse and thus it is necessary to provide appropriate and real-time information for the users. Our research goal is to develop IoT-to-human technologies, which analyze, anonymize, and visualize big data obtained by IoT-based sensing and social media, and provide information in real time by language-centered human-comprehensive multimedia. The IoT-to-human technologies will be extended by utilizing the Deep Learning technologies and applied to the inbound tourism in our project.

Main Research Fields

Computer Science

Related Research Fields

Engineering

Research Subjects

IoT-to-human technologies
Dialog modeling and systems
Speech and natural language processing

Selected Publications

1.Keshi, I., Suzuki, Y., Yoshino, K. and Nakamura. S.:
"Semantically readable distributed representation learning for social media mining"
In Proc. of the 2017 IEEE/WIC/ACM International Conference on Web Intelligence (WI), Aug. 2017
2.Tjandra.A., Sakti.S., Nakamura.S.:
"Compressing Recurrent Neural Network with Tensor Train"
IJCNN 2017, pp. 4451-4458, May 2017
3.Hiraoka,T., Neubig,G., Sakti,S., Toda,T. and Nakamura,S.:
"Learning cooperative persuasive dialogue policies using framing"
Speech Communication, vol.84, pp83-96, Nov. 2016.
4.Maeda,W., Suzuki,Y., and Nakamura,S.:
"Fast Text Anonymization using k-anonymity"
International Conference on Information Integration and Web-based Applications & Services, Nov. 2016.
5.Adams, O., Neubig, G., Cohn, T., Bird, S., Do, Q.T., and Nakamura, S:
"Learning a Lexicon and Translation Model from Phoneme Lattices"
In EMNLP, November 2016.(Best short paper)
6.Do, Q.T., Sakti, S., Neubig, G., and Nakamura, S.:
"Transferring Emphasis in Speech Translation Using Hard-Attentional Neural Network Models."
InterSpeech, pp. 2533 - 2537, Sep. 2016.
7.Tjandra, A., Sakti, S., Manurung, R., Adriani, M. and Nakamura, S.:
"Gated Recurrent Neural Tensor Network"
Proceedings of The 2016 International Joint Conference on Neural Networks (IJCNN 2016), July 2016
8.Misu, T., Sugiura, K., Kawahara, T., Ohtake, K., Hori, C., Kashioka, H., Kawai. H., and Nakamura, S.:
"Modeling Spoken Decision Support Dialogue and Optimization of its Dialogue Strategy"
ACM Transactions on Speech and Language Processing (May 2011), vol.7, no.3, pp10-10:18, 15 Mar. 2011
9.Nakamura, S.,Markov, K., et al. :
"The ATR Multilingual Speech-To-Speech translation system"
IEEE transactions on Audio, Speech and Language Processing, Vol.14, No.2, February, 2006.
10.Nakamura, S.:
"Statistical Multi-Modal Integration for Audio-Visual Speech Processing"
IEEE Transactions on Neural Network, Vol.13, No.4, July 2002

Lab Members

Principal investigator

Satoshi Nakamura: Team Leader

Core members

Sakriani Watiasri Sakti: Research Scientist
Hirohiko Suwa: Research Scientist

Contact Information

B711
8915-5 Takayama Ikoma-city, Nara, Japan
Email: satoshi.nakamura.vr [at] riken.jp