Hi,

I'm Noriko Kando, and coordinating CQA pilot task
together with Daisuke Ishikawa.

Thanks for your interest in NTCIR-8 Community QA (CQA) Pilot
task using "Yahoo! Chiebukuro" data, which is the
Yahoo! Japan's CQA site like Yahoo!Answer.
http://research.nii.ac.jp/ntcir/ntcir-ws8/yahoo/index-en.html

I'm sending this email to explain the status and ask
your opinion and preference for the alternatives for
the schedule and the data set.

The draft data format and task description will be
circulated in the next week through both
this mailing list and the web site.

I'm grateful if we can hear from you !

------------------------------

1. CURRENT STATUS:

With an unexpected situation, the data release has been
tremendously delayed. Currently it is not clear for us
when the data set will be released.

The first (smaller) version has been available from
NII for research purpose since April 2007.
http://research.nii.ac.jp/tdc/chiebukuro_e.html (English)
http://research.nii.ac.jp/tdc/chiebukuro.html  (Japanese)
(sorry, Japanese page contains detalied information)

We planned to use the 2nd (larger) version for this
pilot task.


   table: comparison of 1st and 2nd version data
---------------------------------------------------
ver.    period         size     #Q   #A     avail
---------------------------------------------------
1st: Apr'04 - Oct'05  ca.10GB    3M  13M  already YES
2nd: Apr'04 - Apr'09  ca.100GB* 26M  73M  expected soon,
                                          but not yet
---------------------------------------------------
* The size, the number of questions and answers of
the 2nd version are based on the information we had
in June 2009, but recently it is revealed that
it is smaller than announced (about 2/3 or so).

The 2nd version is richer than the 1st one. For
example, it contains the postings from mobile phones,
etc.



2. POSSIBLE PLANS (SCHEDULE and DATA SET)

Please let us know your opinion, preference or
any other plan.  We are grateful if we can hear
from you!  Any feedback and discussion are
appreciated :-)

----
Plan A:  If the 2nd version available for
NTCIR by the 28th of FEBRUARY, Use 2nd version.

Document release:    16 MAR 2010
Topic release:       30 MAR 2010
Results Submission:   6 APR 2010
Evaluation Result
             Return: 20 APR 2010
Draft Paper Due:      2 MAY 2010
Feedback for the Draft: by 6 MAY 2010
Final Paper Due:     15 MAY 2010
NTCIR-8 Meeting      15-18 JUNE 2010

----
Plan B:  Use the 1st (smaller) version
regardless of the availability of 2nd version.

Document release:    16 MAR 2010
Topic release:       30 MAR 2010
Results Submission:   6 APR 2010
Evaluation Result
             Return: 20 APR 2010
Draft Paper Due:      2 MAY 2010
Feedback for the Draft: by 6 MAY 2010
Final Paper Due:     15 MAY 2010
NTCIR-8 Meeting      15-18 JUNE 2010

----
Plan C:  Use the 2nd (larger) version even if
it will not be available for NTCIR by
the end of February.

Document release:    2 weeks after data receipt
Topic release:       2 weeks after doc. release
Results Submission:  1 week after topic release
Evaluation Result
             Return: 2 weeks after submission
Any paper received by NII by 15 MAY 2010 will
be included the CD and ONLINE Proceedings.

Any paper after 15 MAY will be appeared the
ONLINE Proceedings only.
==============================================

We would love to hear from you!


Thanks in advance,
Noriko and Daisuke
ntcadm-yahoo
---
Noriko Kando
ntcir project