Judith C. Wagner

Tuning up conceptual graph representation for multilingual natural language processing in medicine

Multilingual natural language processing (NLP), whether it concerns analysis or generation of sentences, requires a sound language-independent representation for grasping the deep meaning of narratives. The formalism of conceptual graphs (CGs), especially designed to cope with natural language semantics, constitutes a good repository for dealing with the compositionality and intricacies of medical language. This paper describes our experiment, as part of the European GALEN project, for exploiting a conceptual graph representation of medical language, upon which multilingual medical language processing is performed.

Using the Conceptual Graph Operations for Natural Language Generation in Medicine

Natural language generation systems for the medical domain have to take into account the specific domain vocabulary as well as the particular language style of a highly conventionalised language. This is particularily relevant for multilingual generation.

Mecidal Concept Systems Lexicons and Natural Language Generation

Natural Language Generation (NLG) and Medical Concept Representation can function to mutual benefit. NLG tools need a concept representation system for their semantics, whilst compositional and language independent Medical Concept Representation systems need NLG of readable expressions for composed concepts. To meet these needs, the roles of both sides and their links must be clearly defined. In particular, a clear distinction between concepts, terms and lexical items is necessary. The benefits of linking multilingual lexicons with a concept system are described, together with an architecture designed to integrate NLG within a set of terminological services.