Conceptual structures: information processing in mind and machine
Conceptual structures: information processing in mind and machine
WordNet: a lexical database for English
Communications of the ACM
RelEx---Relation extraction using dependency parse trees
Bioinformatics
Guest Editorial: Current issues in biomedical text mining and natural language processing
Journal of Biomedical Informatics
RelExt: a tool for relation extraction from text in ontology extension
ISWC'05 Proceedings of the 4th international conference on The Semantic Web
Hi-index | 0.00 |
To automatically analyse medical narratives, one needs linguistic and conceptual resources which support capturing of important information from texts and its representation in a structured way. Thus the conceptual structures encoding domain concepts and relations are crucial for the development of reliable and high-performance information extraction system. We present research work enabling automatic extraction of relations between medical concepts. The lack of conceptual resources with Bulgarian ontological vocabulary provoked us to reuse already existing resources with English labels, more especially the UMLS® Metathesaurus®. We form a terminological dictionary of the Bulgarian terms of interest, translate them to English and extract their UMLS definitions which are short English statements in free text. These definitions are processed automatically by a semantic parser; afterwards we apply additional extraction, alternation and validation rules and built a set of new relations to be inserted in our conceptual resource. The article presents the input data and available tools, the knowledge chunks extracted from UMLS and their processing, as well as a discussion of the present results.