[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[eu_members at aclweb dot org] Singapore: ACL-IJCNLP 2009 Workshop on Named Entities Workshop: Shared Task on Transliteration -- CFP


     Named Entities Workshop: Shared Task on Transliteration

     (NEWS 2009 : An ACL-IJCNLP 2009 Workshop)



* Workshop Focus


Named Entities (NEs) play a critical role in Natural Language Processing (NLP)

and Information Retrieval (IR) tasks, such as search, machine translation,

document clustering, summarization, information extraction, etc.  While

identifying and analyzing NEs in a given natural language is a challenging

research problem by itself, the phenomenal growth in the Internet user

population, especially among the non-English speaking parts of the world,

has extended this problem to the cross-language arena, making the handling

of NEs in multiple languages critically important.


The purpose of this workshop is to bring together researchers interested in

various aspects of NEs in natural language text.  In addition, the NEWS workshop

will feature a shared task on Machine Transliteration of NEs.



* Topics of Interest


This workshop invites original research contributions on all aspects of NEs,

including identification, analysis, extraction, mining, transformation and

applications of NE to NLP and IR systems.  The topics of interest include,

but are not limited to the following:


 NE Analysis

   - Distributional characteristics of NEs in mono- & multi-lingual corpora

   - Orthographic/phonetic characteristics of NEs

   - NE origin/genre recognition

   - Social network analysis and entity resolution

 NE extraction

   - Language-independent monolingual NE extraction

   - Cross-language NE extraction

     - General Techniques

     - Specific datasets (Wikipedia, news, etc.)

   - Unsupervised and semi-supervised methods for NE extraction

   - Complex NEs, domain-specific term extraction

   - NE set expansion

   - Creation of annotated data

 Machine Transliteration

   - Computational phonology, incl. modeling of phonological rules, structure,

          behavior, etc.

   - Transliteration modeling

     - Phonetic, grapheme>phoneme and phoneme>grapheme conversions

   - Statistical & machine learning based approaches, transliteration unit alignments

   - Forward and backward transliterations

   - Learning transliteration from comparable corpora

   - Transliteration lexicon construction

   - Romanization of Asian languages

   - Transliteration evaluation metrics 


   - Monolingual and Cross-Language IR, Information Extraction and Management

   - Machine Translation

   - Question Answering

   - Computational Journalism



* Important Dates

Research  Paper Submission Deadline .............1-May-2009

      Task - Registration (Opens)...............16-Feb-2009

      Task - Release Training/Development Data..16-Feb-2009

      Task - Registration (Closes)...............9-Apr-2009

      Task - Release Test Data..................10-Apr-2009

      Task - Results Submission Deadline........14-Apr-2009

      Task - Evaluation Results Announcement....29-Apr-2009

      Short Papers (Task) Deadline...............3-May-2009

Acceptance Notification..........................1-Jun-2009

Camera-Ready Copy Deadline.......................7-Jun-2009

Workshop Date....................................7 Aug 2009



* Paper Submission

Submission to NEWS is through https://www.softconf.com/acl-ijcnlp09/NEWS/.



* Shared Task on Transliteration

Transliteration is defined as phonetic translation of names across languages.

Transliteration of Named Entities (NEs) is necessary in many applications,

such as machine translation, corpus alignment, cross-language IR, information

extraction and automatic lexicon acquisition. All such systems call for

high-performance transliteration, which is the focus of the shared task in

the NEWS 2009 workshop. The objective of the shared task is to promote machine

transliteration research by providing a common benchmarking platform for the

community to evaluate the state-of-the-art technologies. 


Details of the task are available in the workshop homepage, and may also be

downloaded from:




* Organizing Committee

 + Haizhou Li  Institute for Infocomm Research

 + A Kumaran  Microsoft Research India

 + Sanjeev Khudanpur  Johns Hopkins University

 + Raghavendra Udupa  Microsoft Research India

 + Min Zhang  Institute for Infocomm Research

 + Monojit Choudhury Microsoft Research India


* Program Committee

 + Kalika Bali            Microsoft Research India

 + Rafael Banchs          UPC, Spain

 + Sivaji Bandyopadhyay   Univ of Jadavpur, India

 + Pushpak Bhattacharyya  IIT-Bombay, India

 + Monojit Choudhury      Microsoft Research India

 + Marta Ruiz Costa-jussà UPC, Spain

 + Jianfeng Gao           Microsoft Research, USA

 + Gregory Grefenstette   Exalead, France

 + Sanjeev Khudanpur      John Hopkins University, USA

 + Kevin Knight           ISI, USA

 + Greg Kondrak           Univ of Alberta, Canada

 + Olivia Kwong           City Univ, Hong Kong

 + Gina-Anne Levow        Univ of Chicago, USA

 + Arul Menezes           Microsoft Research, USA

 + Jong-Hoon Oh           NICT, Japan

 + Yan Qu                 Advertising.com, USA

 + Dan Roth               Univ of Illinois, Urbana-Champaign, USA

 + Sunita Sarawagi        IIT-Bombay, India

 + Sudeshna Sarkar        IIT-Kharagpur, India

 + Richard Sproat         Univ of Illinois, Urbana-Champaign, USA

 + Keh-Yih Su             Behavior Design Corporation, Taiwan

 + Raghavendra Udupa      Microsoft Research India

 + Vasudeva Varma         IIIT-Hyderabad, India

 + Min Zhang              Institute for Infocomm Research, Singapore


* Workshop & Contact Information

For current information about the workshop, please refer to the workshop

homepage, http://www.acl-ijcnlp-2009.org/workshops/NEWS2009/.