LeARning Foreign LAnguage Scientific Terminology (LARFLAST)

The overall aim of the project is to develop intelligent tools to assist users from some CCE/NIS countries in foreign language learning specifically aimed at the learning of scientific, technical language. The approach of the project will be to apply NLP techniques in developing a generic intelligent foreign language terminology learning system which can easily be adapted to different source languages, target languages and scientific/technical areas.

This will involve the development of language independent knowledge representation (domain knowledge - linguistic, semantic; pedagogical knowledge, etc.) as well as the implementation of a number of multilingual tools to accommodate different source and target languages and technical areas. Within the framework of this project we will consider Bulgarian, Romanian and Russian as possible source languages, English as a target language, and (computer science , business, and communication technologies as technical domains. Some of the developed tools will be fully reusable which will allow adapting the developed system to other source languages, target languages, and technical areas.

The project addresses directly the task of developing multilingual tools for intelligent foreign language learning. The proposed research is intended to make contributions in the following areas:

(a) In developing techniques for improved semantic analysis of learner inputs, with emphasis on work with translation tasks (in either direction) and on work on free-standing text in the language being learnt.

(b) In extending knowledge-based representation techniques to describe technical content in ICALL.

(c) In developing open learner models to allow reflective learning.

(d) In improving methods of foreign language teaching

(e) In applying the techniques in a set of realistic domains, namely:

- to technical university students, professionals, SMEs staff in CCE/NIS.

- to translators in CCE/NIS countries who translate technical texts in unfamiliar domains.

The proposed project will be grounded on a number of models, techniques and tools developed in the partner organisations in their previous research in the following directions: NLP (UMIST); terminology learning (University of Sofia, Simferopol State University); learner modeling (University of Leeds); communicative models in ICALL (Simferopol State University, University of Leeds); agent-based models (University of Milan).

The project will contribute to the involvement of CCE/NIS in the Global Information Society relating directly to the following activities of the Action Plan:

-Multi-lingual support for the Information Society - The project is aimed at developing multilingual tools for teaching scientific foreign language in some CCE/NIS. Thus the project will contribute to breaking down linguistic communication barriers between partners in CCE and in EU.

- Cross-cultural education and training - The result of the project will support innovative language learning which will help preparing professionals, students, SMEs to work effectively in the global market place and lead to a greater understanding of other cultures.


Computer Based Learning Unit, School of Education, University of Leeds, UK.

Department of Information Technology, Faculty of Mathematics and Informatics, University of Sofia "St. Kl. Ohridsky", Bulgaria.

Virtech Ltd, Sofia, Bulgaria.

Department of Information Science, University of Milan, Italy.

Research Center for Machine Learning, Natural Language Processing and Conceptual Modelling, Romanian Academy of Science.

Crimean Research Group "Computers and Languages", State University of Simferopol, Ukraine.

Department of Language Engineering, University of Manchester Institute of Science and Technology.