Tatsuo Yamashita

Yahoo! JAPAN
email: yto at nais.to
http://chalow.net/

Interest

Natural language processing, String searching algorithms, Blog related technologies

Work Experience

Staff Researcher, Fujitsu Laboratories, April 2000 - July 2005

Translation Memory
- Developed a translarion memory engine from scrach (in C++). Fujitsu machine translation software "ATLAS" includes this engine.
- Designed and implemented an graphical interface of the translation memory engine. (implemented as Web application).

Staff Researcher, Yahoo! JAPAN, September 2005 - current

Text Mining

Education

Ph.D Computer Science, Nara Institute of Science and Technology (NAIST), Nara Japan 2002
Studies on Analysis and Retrieval of Large Scale Linguistic Corpus.
- framework of language independent morphological analysis
- graphical user interface which supports an annotator to tag the linguistic information to the plain corpus
- retrieval of annotated corpus
Yuji Matsumoto Lab.

MS Computer Science, NAIST, Nara Japan 1997
Concentration: Natural language processing
Yuji Matsumoto Lab.

BS Computer Science, Hiroshima Univercity, Hiroshima Japan 1995
Concentration: Natural language processing
Yamagata Lab.

Publications(Selected)

Language Independent Morphological Analysis
6th Conference on Applied Natural Language Processing, 2000

Other achievements

Contributer to Chasen - http://chasen.naist.jp/hiki/ChaSen/
Open source Japanese morphological analyzer.
- former dictionary lookup module (PATRICIA Tree)
- graphical interface "ViCha"
- statistics for analysis from POS tagged corpus

SUFARY - http://cl.aist-nara.ac.jp/lab/nlt/ss
String searching library by suffix arrays.

Chalow - http://chalow.org/
Blog tool. It converts ChangeLog files to HTML, but supports most blog technologies such as RSS.

Foreign language Skills

English: TOEIC score 895 (2005)

Computer Skills

Languages: C++, C, Perl, JavaScript
Platforms: Windows, Linux, Solaris