Papers are invited on substantial, original, and unpublished research on application or development of NLP resources, tools and techniques for Less Privileged Languages.
Background and Motivation
While computing has become almost ubiquitous in the US and Europe, its spread in Asia is more recent. However, despite the fact that Asia is a dense area in terms of linguistic diversity (or perhaps because of it), many Asian languages are very inadequately supported on computers. Even basic NLP tools are not available for these languages. This is a major bottleneck in the development of advanced NLP applications and language resources and it also has a social cost.
NLP/CL based technologies are now becoming important and future intelligent systems will use more of these techniques. Most of the NLP/CL tools and technologies are tailored for English or European languages. Recently, there has been a rapid growth of IT industry in many Asian countries. This is the right time to address the lack of computing support and basic NLP tools for less privileged languages. Only when a basic infrastructure for supporting regional languages becomes available can we hope for a more equitable availability of opportunities made possible by computing in general and language technology in particular. There have already been attempts in this direction (some of them are mentioned below) and this workshop will try to take them further, especially in the Asian context.
The purpose of the workshop is to bring together researchers interested in archiving language data, developing language resources, providing basic computing support and creating natural language tools for less privileged languages. Some of these languages are (arguably) Malayalam, Gujarati, Maithili, Assamese, Burmese, Nepali and even tribal languages. They may or may not be low density languages, but the common feature among them is that they are not adequately supported on the computers and not many CL/NLP tools or resources exist for them. The workshop is open to any less privileged (in the above sense) language of the world.
We also invite novel approaches which can exploit the similarities among many languages. One of these similar languages could be a relatively more privileged language and can be treated as a pivot language around which resources and tools are developed for related but less privileged languages such that minimum effort is required. For example, in the South Asian context, Hindi could be treated as the pivot language and the resources and the tools for languages like Punjabi, Urdu, Gujarati etc. could be developed as extensions of (or projections of) the resources and tools for Hindi. Perhaps minimally supervised algorithms could be used to achieve this goal.
Papers are invited on substantial, original and unpublished research on following aspects of NLP for LPL, including but not limited to:
- Archiving and creation of interoperable data and metadata for less privileged languages.
- Support for less privileged language on computers. This includes input methods, display, fonts, encoding converters, spell checkers, more linguistically aware text editors etc.
- Basic NLP tools such as sentence marker, tokenizer, morphological analyzer, transliteration tools, language and encoding identifiers etc.
- Advanced NLP tools such as POS taggers, local word grouper, approximate string search, tools for making development of language resources easier etc.
Paper submission is through the centralized workshop submission page. Papers have to be written in English. There are two categories of papers: long and short. Long papers can be up to 8 pages long, while the maximum length for short papers is 5 pages (including references, figures, tables etc.). All selected papers will be published in the workshop proceedings.
The papers should be formatted using the LaTeX styles or MS Word templates recommended for the main IJCNLP conference. These documents are available here. Reviewing will be blind. The draft papers should not contain any information that can identify the authors, as far as possible.
- Paper Submission Deadline:
Sept 21, 2007 Sept 25 (11:59 pm PST)
- Notification of Paper Acceptance:
Oct 26, 2007 Nov 5, 2007
- Camera Ready Submission Deadline: Nov 16, 2007
Steven Bird, University of Melbourne, Australia
Rajeev Sangal, IIIT, Hyderabad, India
Michael Maxwell, University of Maryland, USA
Bente Maegaard, CST, University of Copenhagen, Denmark
Lakshmi Bai, IIIT, Hyderabad India
Emily M. Bender, University of Washington, USA
Nicoletta Calzolari, Istituto di Linguistica Computazionale del CNR - Pisa, Italy
Alexander Gelbukh, Center for Computing Research, National Polytechnic Institute, Mexico
Sarmad Hussain, CRULP, Pakistan
Greville Corbett, University of Surrey, UK
Anil Kumar Singh, IIIT, Hyderabad, India
Sobha L., AU-KBC, Chennai, India
Rachel Edita Roxas, Dela Salle University, Manila, Philippines
Sivaji Bandyopadhyay, Jadavpur University, Kolkata, India
Nicholas Thieberger, University of Melbourne, Australia
Monojit Choudhury, Indian Institute of Technology, Kharagpur, India
Xabier Arregi, University of the Basque Country, Spain
Khalid Choukri, ELRA - Paris, France
Samar Husain, IIIT, Hyderabad, India
Indra Budi, University of Indonesia, Indonesia
Rajat Mohanty, Indian Institute of Technology, Mumbai, India
Jeff Good, University at Buffalo, USA
Prasad Pingali, IIIT, Hyderabad, India
Harshit Surana, IIIT, Hyderabad, India
Anil Kumar Singh
Language Technologies Research Centre
International Institute of Information Technology
Gachibowli, Hyderabad, India
Phone: 91-40-23001412, 91-40-23001967/9 Extension 144