На български

Research

One of the main goals of the Association is the participation and initiation of scientific research projects in the area of Computational Linguistics. It brings together and manages scientists from different backgrounds and builds teams of experts for research goals. A considerable amount of experience, know-how and resources have been gained in carrying out these activities. Members of the Association have been actively participating in European and Bulgarian scientific projects for more than ten years. Some of the projects are listed below:

• 2002-2004 OCoRrect (Cyrillic and Latin OCR correction using electronic dictionaries and sentence context), Volkswagen Stiftung, Ref: I 77 863
  The OCoRrect project develops methods and algorithms for automatic text correction for Bulgarian, German, English and Russian. The methods are based on the use of large-scale multilingual electronic dictionary and sentence context analysis.
• 2001-2004 BalkaNet (A Multilingual Semantic Network for the Balkan Languages), IST-2000-29388
  The BalkaNet project aims at building a multilingual lexical database consisting of WordNets in several Central and Eastern European languages. Each language-specific WordNet will be structured along the same lines as the Princeton WordNet and the EuroWordNet.
• 2002-2003 Correction and Equalization Methods for textual information, Bulgarian Association for Computational Linguistics.
  The goal of the project is recognition and adequate correction of errors in electronic text fragments from various sources (typed texts, Optical character recognized texts, Speech recognized texts etc.).
• 1999-2003 Bulgarian INTEX, Bulgarian Association for Computational Linguistics
  INTEX is a linguistic development environment that includes large-coverage dictionaries and grammars, and parses texts of several millions words in real time. INTEX includes tools to create and maintain large-coverage lexical resources, as well as morphological and syntactic grammars.Large-coverage Bulgarian INTEX module has been developed by Sofia INTEX research team.
• 1999-2002 TELRI II (Trans-European Language Resources Infrastructure), CA INCO-Copernicus 97/98, PL97-7085
  TELRI is an initiative which is creating a viable infrastructure between leading European language and language technology centres in order to provide a platform for industry, research institutes and universities and to supply the NLP community with public domain monolingual and multilingual language resources.