The second Chinese Language Processing Workshop
Sponsored by SIGLEX, SIGDAT and SIGPARSE.
October 2000
Hong Kong University of Science and Technology
In conjunction with ACL-2000
Growing
interest in Chinese Language Processing is leading to the development of
resources such as annotated corpora and automatic segmenters, part-of-speech
taggers and parsers. The first Asia
ACL provides an ideal opportunity to bring together influential researchers from
Taiwan, Singapore, Hong Kong, and Beijing, as well as Chinese language
researchers in the rest of the world, to discuss issues that are specific to the
processing of Chinese. A critical tool for developing Chinese language
processing tools is the availability of annotated corpora.
The greater the consensus we have around guidelines for corpus annotation
of part-of-speech tags, syntactic bracketing and other areas, the more useful
this corpora will be.
We welcome submissions that address the following topics on Chinese language
processing:
. word segmentation
. POS tagging
. phrase identification
. parsing
. grammar development
. lexicon acquisition
. corpus development
We invite workshop participants to take advantage of two bracketed corpora:
. The first one, Chinese Penn Treebank, was developed at
University of Pennsylvania, USA. It includes 100-thousand words from Xinhua
News.
The corpus has been released via LDC at UPenn.
For more information
and the release announcement, please check the website http://www.ldc.upenn.edu/ctb/
. The second one, developed by
CKIP, Academia Sinica in Taiwan, contains more than 30,000 sentences. A trial
version of 1,000 sentences is now available for download by the public at
http://godel.iis.sinica.edu.tw/CKIP/trees1000.htm
The release of the
complete treebank is being reviewed by Academia Sinica.
Preliminary
arrangements have been made for the treebank to be licensed through ROCLING.
Please check their website
(http://rocling.iis.sinica.edu.tw/ROCLING)
for announcement.
The workshop will be held either on Oct 7 or Oct 8. For latest update of the
workshop, please check http://www.ldc.upenn.edu/ctb/clp00.html
If
you have any questions concerning the workshop or the Treebank, please email us
at chinese@linc.cis.upenn.edu.
Submissions:
Submissions are limited to original, unpublished work. Papers may not exceed
3200 words (exclusive of title page and references). Papers outside the specified
length are subject to be rejected without review. The paper should be written in
English.
The style files for submission are the same as the ones for ACL regular paper,
which can be downloaded from http://www.cs.ust.hk/acl2000/fcfp.html.
The reviewing of papers will be blind. Hence the title page and paper should not
include the authors' names and affiliations. Furthermore, self-references that
reveal the author's identity (e.g., "We previously showed (Smith, 1991)
...") should be avoided. Instead, use citations such as "Smith
previously showed (Smith, 1991)...".
As reviewing will be blind, a separate title page and identification page will
be required. The title page should include the following information:
Title:
Paper ID
Code: just put "00"
Topic Area: one or two general topic areas
Keywords: Up to 5 keywords specifying subject area
Which Session: just put "G"
Word Count,
excluding title page and references:
Under Consideration for other Conferences (specify):
Abstract: short summary (up to 5 lines)
The identification page should contain all of the information in the title page,
but in addition must include the authors' names, affiliations, and email
addresses. The format for the identification page should be as follows:
Title:
Paper ID Code: just put
"00"
Authors' names, affiliations, and email addresses
Topic
Area: one or two general topic areas
Keywords: Up to 5 keywords specifying subject area
Which Session: just put "G"
Word Count, excluding title page and references:
Under Consideration for other Conferences (specify):
Abstract:
short summary (up to 5 lines)
Submissions must be received by July 1, 2000. Late submissions (those arriving
on or after July 2) will be rejected without review. The Program Committee is
not responsible for postal delays or other mailing problems. Six (6) paper
copies (printed on both sides of the page if possible) including the title page
plus two (2) identification pages should be submitted to the following address:
CLP-2000 submission
c/o Fei Xia
Institute for Research in Cognitive Science (IRCS)
3401 Walnut St. Suite 400A
Philadelphia, PA 19104, USA
Also, a postscript version of the paper (EXCLUDING the ID page) must be emailed
to chinese@linc.cis.upenn.edu on
or before July 1. Once the submission is received, a paper ID will be assigned
to the paper and this ID number will be emailed to the authors. The authors
should include the ID number in the subject lines in subsequent email exchanges.
Important Dates:
July 1, 2000
Submission of full-length paper
August 10, 2000
Acceptance notice
September 5, 2000
Camera-ready paper due
October 1 or 2
Conference date
Organizational committee:
Martha
Palmer - UPenn
Mitch Marcus
- UPenn
Fei Xia -
UPenn
Aravind
Joshi - UPenn
Program committee:
Nianwen Xue - U of Delaware, USA
Shengli Feng - U of Kansas, USA
K.L.Kwok - Queens College, USA
Wanying Jin - New Mexicon State University, USA
Amy Weinberg - U. of Maryland, USA
Mary Ellen Okurowski - Department of Defense, USA
John Kovarik - Department of Defense, USA
Andi Wu - Mircrosoft, USA
Bangalore Srinivas - AT&T Research Lab, USA
Laurie Gerber - Systran, USA
Jin Yang - Systran, USA
Ralph Weischedel - BBN, USA
Dong Zhendong - Hownet designer, China
Shiwen Yu - Peking University, China
Qiang Zhou - Tsinghua University, China
Chunfa Yuan - Tsinghua University, China
Maosong Sun - Tsinghua University, China
Joe Zhou - Intel China Research Center, China
Chang-Ning Huang - Microsoft Research, China
Gan Kok Wee - Hong Kong Science and Technology University
Dekai Wu - Hong Kong Science and Technology University
Benjamin K Tsou - Hong Kong City Univeristy
Keh-Jian Chen - Academia Sinica, Taiwan
Chu-ren Huang - Academia Sinica, Taiwan
Keh-Yih Su - Behavior Design
Corporation, Taiwan
Lua, Kim-Teng - National University of Singapore
Tan Chew Lim - National University of Singapore
Fuji Ren - Hiroshima City University, Japan