This is a job at ATR in Kyoto, Japan that starts this Spring, or as
soon thereafter as possible, and lasts for a year to a year and a
half.
The slot is for someone with heavy C++ experience and skills, who is
also a seasoned applied mathematician with expertise in prediction,
and who has spent time in industry, on large-scale, real-world
prediction problems.
For the past two years, this job has been occupied by Stephen Eubank,
of SFI, The Prediction Company, and Los Alamos. He is now ready to
move on, but has enjoyed his work and his life here, and anyone
considering this job may wish to contact him at eubank@itl.atr.co.jp
for his views and experiences here. (You might also contact Tom Ray,
ray@hip.atr.co.jp, who has been at ATR for the past three years, to
ask about life at this lab, and in Japan, more generally.)
Previous to that, the job belonged to Turing International Programming
Prize-winner David Magerman, formerly of IBM Watson Research Center,
then BBN, and now an equity-"quant"-fund technical manager with
Renaissance, Inc. We also have an ongoing consultancy relationship
with John Lafferty, a research professor at CMU, and prior to that at
IBM Watson Research, and before that, of the Harvard math faculty. The
person who takes on the job we're talking about would be interacting
with John, as well as with other interesting people in the field of
prediction.
Basically this job has two aspects: (1) maintaining and
troubleshooting a large C++ system we have created, which
probabilistically assigns grammatical structure to English sentences
(i.e. "diagrams" or "parses" sentences); our current models use
CART-type probabilistic decision trees; and (2) experimenting with
variations on our current models, so as to improve performance. The
purpose of the parsing program is to help in tasks such as
speech-to-speech Japanese-to-English translation (we are working on a
Japanese version of the software as well); speech and handwriting
recognition; and information retrieval. Projects of all these sorts
exist in the ATR laboratories, and one of the satisfactions of this
job will probably be seeing this software "plugged into" such
applications over the next year or so.
Salary and conditions are all quite competitive. Serious candidates
should be driven both by the technical challenge and by a sense of
adventure, since life in Japan is very different from Western life in
any country, and one needs a genuine curiosity plus a sense of humor
to enjoy it. Also, please apply only if you're a very hard worker; we
have a lot to get done in the next year and a half or so.
Here is the ad we've been circulating for this position. Please
contact black@itl.atr.co.jp if this job interest you. Thanks very
much.
Ezra Black
Manager
Statistical Parsing Group
Natural Language Processing Department
Interpreting Telecommunications Laboratories
Advanced Telecommunications Research Laboratories (ATR)
Kyoto, Japan
--------------------
Mathematician (Probability) / Programmer Job Opportunity
Statistical Natural Language Processing
ATR Interpreting Telecommunications Research Laboratories
Kyoto, Japan
ATR in Kyoto, Japan is looking for a talented and experienced
mathematician (good probability background) / computer scientist who
is interested in coming to Japan and joining an exciting research
project in statistical natural language processing. The overall goal
of the project is speech-to-speech Japanese to English and English to
Japanese translation. The research group which the candidate would
become part of has developed and is refining a natural language
parsing system based on statistical machine learning algorithms.
A qualified candidate must have the Ph.D. degree, preferably math,
physics, computer science; with extensive programming experience and
expertise in C++. Ability to innovate approaches to applied
mathematical problems in the area of probability required. Experience
with statistical modelling within general pattern recognition field
also important. Familiarity with natural language field a plus but not
absoutely necessary. Candidate should know UNIX well and in general be
a highly expert programmer. This is not a job for those who are
theoreticians only, but rather is for someone who is equally at home
with issues of statistical modelling theory, experimental method, and
detailed coding matters. Motif experience would be nice, though again
not required. The position involves supervision of several researchers
and programmers as well.
Salary and conditions highly competitive.
Please contact: black@itl.atr.co.jp. Thank you.