Professor at the Bulgarian Academy of Sciences
Director of the Institute for Bulgarian Language
Chair of the Department of Computational Linguistics
52 Shipchenki prohod, bl. 17, 1113 Sofia (Bulgaria)
My research interests are in the field of:
- Computational Linguistics and Natural Language Processing;
- Problems of Formal Natural Language Description;
Current priorities are oriented towards:
- Problems of machine translation;
- Corpus studies;
- Syntactic parsing.
Resources and software:
- Spelling Checking for Bulgarian: ItaEst – taka e!, WinEst for Microsoft Office, MacEst for Mac OS, WebEst for online integration. The Spelling Checking is based on the large Grammatical Dictionary of Bulgarian, consisting of over 85 000 lemmas and 1 400 000 word forms.
- Main researcher and coordinator of the development of several very large linguistic resources for Bulgarian: Bulgarian WordNet – a lexical-semantic network, consisting of over 83 000 synsets; Bulgarian National Corpus; PoS and Sense annotated Bulgarian corpora, Bulgarian-English Sentence- and Clause-Aligned Corpus, Bulgarian FrameNet, etc.
- Main researcher and coordinator of the development of basic tools for processing Bulgarian: Language processing chain (tokenizer, sentence splitter, morphological analyzer, tagger, lemmatizer), development of different types of grammars (phrase-structure, named entities recognition) implemented in Press clipping and Business intelligence services, etc.