The Institute for Bulgarian Language “Prof. Lyubomir Andreychin” at the Bulgarian Academy of Sciences is the major center for scientific research of the Bulgarian language focusing on its current state, history, dialect diversity and interrelation with other languages. Researchers at the IBL successfully participate during the last five years in international projects under the EU programs in FP5 (BalkaNet), FP6 (Knowledge Transfer for Digitalization of Cultural and Scientific Heritage in Bulgaria), FP7 (Common Language resources and Technologies Infrastructure), and the Leonardo da Vinci Program (Language in Tourism). The Department of Computational Linguistics carries out theoretical and applied research in the field of natural language processing. IBL DCL is involved in a number of projects dealing with theoretical issues in the formal description of language, morphological, syntactic and semantic analysis, electronic dictionaries, ontologies and semantic relations, corpus linguistics, document categorization and annotation, information extraction and retrieval, Part of Speech (PoS) and Word Sense disambiguation, spelling and grammar checking, machine translation, etc.

The IBL DCL will bring to the consortium substantial expertise in natural language processing as well as significant experience in national and EU projects. Their role is considerable, as their contribution will address the need for NLP tools for the other newest language in the EU community – Bulgarian. The following major tasks will be performed by IBL DCL:

• T3.2 – Fine-tuning of the categorization tool to Bulgarian
• T4.1 – Implementation of a language processing chain for Bulgarian
• T5.1 – Implementation of a text summarization tool for Bulgarian