LREC02. SALTMIL workshop. Portability Issues in Human Language Technologies (HLT)
In June 2002, a workshop following the Third International Language Resources and Evaluation Conference LREC 2002 was held in Las Palmas de Gran Canaria, Spain.
Motivation and Aims
There are more than 6000 languages in the world, yet only a small number possess the resources required for implementation of Human Language Technologies (HLT). This imbalance in technical resources available to languages of the world is likely to result in a significant linguistic divide that further exacerbates global social and economic inequities unless decisive action is taken relatively soon. One potential means of ameliorating this imbalance in technology resources is through encouraging research in the portability of human language technology for multilingual application.
Portability issues in HLT are important in the structuring and acquisition of local language resources. The primary objective of the workshop is to bring together participants from academia and industry to discuss and disseminate the current state of the art in multilingual research and development in the context of cross-language HLT transfer. Major challenges for HLT-portability research will also be discussed.
The workshop will focus on the following topics and languages:
- Linguistic corpora and portability (new models, language maps, novel systems for creating and managing multilingual data).
- Automatic Speech Recognition (generic design in acoustic modelling, task portability, cross-language portability):
- Acoustic modelling (monolingual and multilingual modelling, cross-language transfer, finite state automata,decision trees and data-driven methods).
- Dictionary development (word-definition issues, automatic dictionary acquisition).
- Language modelling (the Internet as a linguistic resource, language modelling in spoken language processing).
- Natural Language Processing (cross-language transfer of HLT):
- Parsing.
- Translation.
The proposed workshop is intended to continue the series of SALTMIL (ISCA SIG) LREC workshops related to the integration of local and global languages ("Language Resources for European Minority Languages" (LREC'98)) as well as the workshop on "Developing Language Resources for Minority Languages: Re-usability and Strategic Priorities" (LREC'00)).
Workshop Agenda
14:30 Registration, and preparation of posters
Oral Session: Portability Issues in HLT
| 14:50 | Workshop Welcome and Introduction | Bojan Petek |
| 14:55 | Multilingual Time Maps: Portable Phonotactic Models for Speech Technology | Julie Carson-Berndsen |
| 15:20 | Units for Automatic Language Independent Speech Processing |
Jan Černocký |
| 15:45 | Some Issues in Speech Recognizer Portability | Lori Lamel |
| 16:10 | Seven Dimensions of Portability for Language Documentation and Description | Steven Bird and Gary Simons |
16:35 Break
Oral Session: HLT and the Coverage of Languages
| 17:00 | Challenges and Opportunities in Portability of Human Language Technologies |
Bojan Petek |
| 17:25 | The Atlantis Observatory: Resources Available on the Internet to Serve Speakers and Learners of Minority Languages |
Salvador Climent, Miquel Strubell, Marta Torres, and Glyn Williams |
| 17:50 | Towards the definition of a basic toolkit for HLT | Kepa Sarasola |
18:15 Poster Session
| Ubiquitous Multilingual Corpus Management in Computational Fieldwork | Dafydd Gibbon |
| A Theory of Portability | Hyo-Kyung Lee |
| A Requirement Analysis for an Open Set of Human Language Technology Tasks | Fredrik Olsson |
| Taking Advantage of Spanish Speech Resources to Improve Catalan Acoustic HMMs | Jaume Padrell and José B. Mariño |
| Portability Issues of Text Alignment Techniques |
António Ribeiro, Gabriel Lopes, and João Mexia |
| SPE Based Selection of Context Dependent Units for Speech Recognition | Matja Rodman, Bojan Petek, and Tom Brøndsted |
| VIPTerm: The Virtual Terminology Information Point for the Dutch Language. A Supranational Project on Terminology Documentation and Resources | Frieda Steurs |
20:00 End
Workshop Organizing and Program Committee
| Julie Carson-Berndsen | University College Dublin | Dublin, Ireland |
| Steven Greenberg | International Computer Science Institute | Berkeley, USA |
| Bojan Petek | University of Ljubljana | Ljubljana, Slovenia |
| Kepa Sarasola | University of the Basque Country | Donostia, Basque Country |
Submission
Papers are invited that describe research and development in the area of Human Language Technology portability. All contributed papers will be presented in poster format. Each submission should include: title; author(s); affiliation(s); and contact author's e-mail address, postal address, telephone and fax numbers. Abstracts (maximum 500 words, plain-text format) should be sent via email to:
This e-mail address is being protected from spambots. You need JavaScript enabled to view it
All contributed papers will be printed in the workshop proceedings.
Important Dates
| Deadline for workshop abstract submission | 8th March 2002 |
| Notification of acceptance | 15th March 2002 |
| Final version of the paper for the workshop proceedings | 8th April 2002 |
| Workshop | 1st June 2002 |
Workshop Registration Fees
The registration fees for the workshop are:
- If you are not attending LREC: 70 EURO
- If you are attending LREC: 45 Euro
These fees cover the following: a copy of the proceedings of the attended workshop, coffee-breaks and refreshments.
Participation in the workshop is limited by the venue. Requests for participation will be processed on first come first served basis. Registration will be handled by the LREC Secretariat.