Department of Linguistic Modelling and Knowledge Processing


Linguistic resources and tools

  • BulTreeBank – An HPSG-based treebank of Bulgarian;
  • BulTreeBank Text Archive – Texts annotated up to paragraph level with respect to TEI guidelines;
  • BulTreeBank Morphosyntactic Corpus – Texts annotated with grammatical information;
  • Bulgarian CLEF Corpus – Supporting the evaluation of question answering and information retrieval systems for Bulgarian;
  • Bulgarian LT4eL Corpus - Grammatical and semantic annotation;
  • Morphological Dictionary of Bulgarian;
  • BulTreeBank Gazetteers – Lexicon of proper names;
  • BulTreeBank Partial Grammar – simple NPs and verb forms;
  • Parallel Bulgarian-English HPSG Treebank;
  • Dependency Parser for Bulgarian;
  • POS Tagging for Bulgarian;
  • Bulgarian resources for CLEF (Cross-Language Evaluation Forum);
  • Medical text processing;
  • Applications of Finite State Technologies in text scanning and processing.



AIMSA 2016

Artificial Intelligence: Methodology, Systems, Applications

W3C Validator