[Corpora-List] IJCNLP-04 Newsletter No.2 (20th of Oct. 2003)
Hitoshi Isahara
isahara at crl.go.jp
Wed Oct 22 06:18:45 UTC 2003
==========================================================================
*********** IJCNLP-04 Newsletter No.2 (20th of Oct. 2003)***************
The 1st International Joint Conference of Natural Language Processing
organized by the Asia Federation of NLP associations (AFNLP)
Website:
http://www.cipsc.org.cn/IJCNLP-04/
http://www.rcl.cityu.edu.hk/ijcnlp04 (mirror site in HK)
http://www.colips.org/conference/ijcnlp04/ (mirror site in Singapore)
http://www.isi.edu/natural-language/ijcnlp04 (mirror site at USC)
************************************************************************
[Date]
Main Conference: March 22-24, 2004
Workshops: March 25, 2004
[Venue]
Sanya, Hainan island, China
***Land's End - Hainan is so remote on the sea that ancient people,
while believing that earth is square, really thought it is where
the land ends***
http://www.regenttour.com/chinaplanner/hainan/
[Sponsoring Organizations]
Chinese Information Processing Society of China
Association for Natural Language Processing of Japan
Association for Computational Linguistics
Korea Natural Language Processing Society (SIG-KLC)
(to be added)
************************************************************************
This issue contains
[0] New sponsorship
[1] Paper submission
[2] Publication
[3] Tutorials
[4] Workshops
[5] Satellite Symposium (call for extended abstract)
************************************************************************
[0] New Sponsorship
We are pleased to announce that Korea Natural Language Processing Society (SIG-KLC) has offered financial support to IJCNLP-04. We will welcome like-minded supports from professional bodies and industrial partners. Please contact us to:
Benjamin Tsou : rlbtsou at cityu.edu.hk
------------------------------------------------------------------------
[1] Paper Submission
The information on paper submission will soon appear in the website
http://www-tsujii.is.s.u-tokyo.ac.jp/ijc-nlp04/submission.html
The important dates are as follows.
Paper submission deadline: November 15, 2003
(Note that we abolish the paper registration deadline of November 8)
Notification of acceptance: December 23, 2003
Camera ready papers due: January 24, 2004
------------------------------------------------------------------------
[2] Publications Policy
We have negotiated with ACL and Springer for publication and archiving of our proceedings as follows:
(1) The proceedings of the main conference will be archived in the ACL anthology site after the conference.
(2) A book of selected papers of the conference will be published in LNAI (Lecture Notes in Artificial Intelligence) by Springer after the conference at the earliest possible time.
-------------------------------------------------------------------------
[3] Tutorials
There will be the following two tutorials on the 21st of March.
(a) [Tutorial 1] Pitfalls in Applying Unsupervised Learning to NLP
Hours: 3 hours
Speakers:
Jing-Shin Chang (National Chi-Nan Univ., Taipei)
Keh-Yih Su (Behavior Design Corporation, Taipei)
Summary:
Unsupervised learning is getting more and more popular in the NLP community, since large-scale un-annotated corpora are increasingly available at almost no cost and unsupervised learning approaches provide the capability to directly utilize such un-annotated corpora. However, the results may not be optimal or may even be unsatisfactory if the learning procedure is not conducted properly.
In this tutorial, we will first identify some frequently unnoticed pitfalls that might prevent the unsupervised learning from getting good performance. The suggested strategies for avoiding such pitfalls are then proposed.
(b) [Tutorial 2] HowNet
Hours: 3 hours
Speaker: Dong Zhen Dong
Summary: This tutorial addresses issues on building a large semantic-oriented lexical resource. The talk focuses on HowNet that the speaker has been engaged in developing. It will include, (1) Overall picture of HowNet, (2) HowNet-based second resources, (3) Comparison between HowNet and WordNet, SUMO, VerbNet, (4) Some typical applications of HowNet
-------------------------------------------------------------------------
[4] Workshops
The following three workshops will take place as post-conference workshops on March 25. The details of the workshops such as their submission sites etc. will be available from our webistes (http://www.cipsc.org.cn/IJCNLP-04/, http://www.rcl.cityu.edu.hk/ijcnlp04 (mirror site in HK), http://www.colips.org/conference/ijcnlp04/ (mirror site in Singapore).
------
(a)[Workshop 1] Asian Language Resources
Asia, the land of language variation, are suffering from the shortage of sharing the resource and cross language problem solving experience. There are several reports referring to the success of constructing and using corpora in many dimensions. However, there are few efforts in establishing common formats or frameworks for handling these languages. The re-organizing the existing resources and finding for the guideline in corpus development become significant issue in the current research.
The 4th workshop on Asian Language Resources will be held with the following purposes:
- To investigate and discuss the problems related to the construction, dissemination and NLP research based on Asian Language Resources
- To establish the collaborative effort on Asian language resources construction, management, accessibility, distribution, and sharing
- To launch the Asian Language Resources road map
- To introduce the status of Asian language resources to researchers in other regions
Topics of interest include, but are not limited to:
* Text corpora * Machine-readable dictionaries
* Lexicons * Ontology
* Grammars * Exchange and annotation schemata
* Infrastructure for constructing and sharing language resources
* Exchange formats
* Best practices for creating and disseminating language resources
* Meta data for resource classification and discovery
* Strategies and priorities for EU-US and Asian cooperation
* Standards for language resources (lexicons, corpora, ontologies, etc.)
* Lexical standards and multi-linguality
* Standards for content management
* Standards and applications * Standards and evaluation
Chair: Virach Sornlertlamvanich
Thai Computational Linguistics Laboratory, CRL, Bangkok
Co-chairs: Chu-Ren Huang,(Academia Sinica, Taipei)
Takenobu Tokunaga,(Tokyo Institute of Technology, Tokyo)
Important dates:
Paper submission deadline: December 12, 2003
Notification of acceptance: January 10, 2004
Camera ready papers due: January 24, 2004
Workshop date: March 25, 2004 (Thursday)
------
(b) [Workshop 2] Multilingual Summarization and Question Answering
- Towards Systematizing and Automatic Evaluation
Website: http://www.isi.edu/~cyl/msqa-eval-ijcnlp04/
Automatic summarization and question answering (QA) are now enjoying a period of revival and they are advancing at a much quicker pace than before. Recently in the United States, TREC started an English QA track in 1999 and DUC sponsored by NIST also started a new English summarization evaluation series in 2001. In Japan, NTCIR project included Japanese text summarization task in 2000 and QA task in 2001.
One major challenge of these large scale evaluation efforts is how we can evaluate summarization and QA systems systematically and automatically. In other words, is there a consistent and principled way in estimating the quality of any summarization and QA system accurately and can we automate the evaluation process? The release of the "Framework for Machine Translation Evaluation in ISLE (FEMTI)" and the recent adoption of the automatic evaluation metric, BLEU, in the machine translation community are good examples that we might be able to find leverage from and extend them to summarization and QA evaluations.
This workshop focuses on automatic summarization and QA, and enable participants to discuss the integration of multiple languages and multiple functions and most importantly how to robustly estimate quality of summarization and QA..
Organizers: Chin-Yew Lin (USC/ISI, Los Angeles)
Hang Li (Microsoft Research Asia, Beijing)
Important dates:
Paper submission deadline: December 12, 2003
Notification of acceptance: January 10, 2004
Camera ready papers due: January 24, 2004
Workshop date: March 25, 2004 (Thursday)
-------
(c) [Workshop 3] Beyond shallow analyses
-Formalisms and statistical modeling for deep analyses-
Corpus-based methods both in linguistics and NLP need breakthroughs for further development. Applications such as machine translation, Q/A with deductive inference ability, intelligent dialogue systems, etc. require deeper representation of meanings than surface constituent structures. Machine learning techniques also have to exploit more linguistically motivated features. Combining corpus-based methods with linguistic formalisms may give rise to a new type of linguistics.
This workshop addresses issues such as
(1) Corpus annotation beyond surface constituent structures
(2) Grammar acquisition from annotated corpora based on linguistic theories
(3) Methods of combining linguistic formalisms with statistical modeling
(4) Corpus-based techniques enhanced by linguistic formalisms
Organizers:
R. Kaplan (Parc, Palo Alto)
M. Johnson (Brown University, Rhode Island)
A. Joshi (University of Pennsylvania, Philadelphia)
S. Riezler (Parc, Palo Alto)
J. Tsujii (University of Tokyo, Tokyo) *contact person
H. Uszkoreit (DFKI and Saarbrueken University, Saarbrueken)
(Two or three will be added to the list)
Paper submission:
January 31, 2003
Notification of acceptance: February 20, 2003
(This WS will not prepare a printed version of the proceedings. Participants are expected to download papers to be presented and bring them to the site. However, we plan to publish a post-workshop proceedings as a book.)
-------
(d) [Workshop 4] Named Entity Recognition for Natural Language Processing Applications
Named Entities (NEs) are communicatively loaded items which are pervasive and of critical importance in human verbal interaction. They constitute an area of major significance in NLP. The recognition of proper names as unknown words has long been an issue in word segmentation and part-of-speech tagging, especially for non-alphabetic Asian languages and inter-lingual MT involving these languages. Named entities often represent indispensable targets in information extraction. Proper transliteration of named entities, especially proper names, is critical for the intelligibility and accuracy of machine translation output. This workshop aims at bringing together researchers of diverse background to discuss the issue and advances in NE recognition and extraction, and how NE could be handled most cost-effectively in a variety of NLP applications.
Papers are invited for original and unpublished research on all aspects of
NE recognition and extraction, including but not limited to:
- Symbolic and statistical models for NE recognition
- NE recognition systems
- Translation of NEs across multiple languages
- Resources (lexicons, grammars) for NE extraction
- NE recognition as a sub-task in NLP applications
- Evaluation of NE processing in NLP applications
Organizer: Benjamin Tsou (City University of Hong Kong、Hong Kong)
Important Dates
Submission Deadline: 8 December 2003
Notification of Acceptance: 8 January 2004
Camera-Ready Paper Due: 24 January 2004
Workshop Date: 25 / 26 March 2004
-------------------------------------------------------------------------
[5] Satellite Symposium : Asian Symposium on Natural Language Processing to Overcome Language Barriers
++++++++++++++
Organized by:
The Institute of Electronics, Information and Communication Engineers (IEICE)
Technical Group on Natural Language Understanding and Models of Communication (NLC)
Technical Group on Thought and Language (TL)
Supported by: Communications Research Laboratory (CRL)
[Date] March 25-26, 2004
[Venue] Hainan Island, China
[Contact Person] IZUHA Tatsuya, Toshiba Corporation (tatsuya.izuha at toshiba.co.jp)
++++++++++++++
The Internet has made it easy to access to a vast amounts of information and to connect with people all over the world. However, there are numerous barriers to effective information access and efficient communication. One of these is language differences. Gaps between different kinds of media, such as speech and text, also
decrease the efficiency of information access. The handicapped and the aged are faced with many more barriers than these. This symposium aims to bring together NLP researchers in Asia and to discuss how language barriers can be overcome by applying Natural Language Processing.
Topics of interest include, but are not limited to:
* Cross-lingual information access and communication
Machine translation, Speech translation,
Cross-lingual information retrieval / question answering,
Multilingual automatic summarization, Language education
* Cross-media information access
Text retrieval / question answering by speech
Multimedia data retrieval
* Information access and communication for the handicapped and the aged
Closed-caption generation, Sign language translation
Braille transcription
* Basic technology for Making language barrier-free
Natural language analysis, Natural language generation
[Submission]
The submission deadline of extended abstracts will be December, 2. Submission details will be available from
http://www.ieice.org/iss/nlc/jpn/symposium2004e.html
[Publication]
This Symposium will prepare a printed version of the proceedings. We also plan to publish selected papers as a special issue of IEICE Transactions.
[Important Dates]
Submission of Extended Abstracts December 2, 2003
Notification of Acceptance December 23, 2003
Camera Ready Papers February 23, 2004
Symposium March 25-26,2004
[Organizing Committee]
ISAHARA Hitoshi (Co-chair) - Communications Research Laboratory
NITTA Yoshihiko (Co-chair) - Nihon University
AKIBA Tomoyoshi
- National Institute of Advanced Industrial Science and Technology
INUI Kentaro - Nara Institute of Science and Technology
UTSURO Takehito - Kyoto University
FUKUMOTO Jun'ichi - Ritsumeikan University
NAKANO Mikio - Nippon Telegraph and Telephone Corporation
==========================================================================
More information about the Corpora
mailing list