Towards a UMLS-Integratable Vietnamese Medical Terminology

Abstract

Lexical resources play an essential role in text processing. In this paper, we present our work on the construction of a Vietnamese medical terminology integratable into the UMLS multilingual metathesaurus (Unified Medical Language System). The construction of the Vietnamese medical terminology is done by collecting terms from existing lexical sources on one hand, and by extracting terms from Vietnamese medical corpora on the other. In order to draw maximum benefit from the varied sources and corpora that can be collected, we have developed a set of tools adapted to the specificities of each of those resources, based upon proven techniques. This allows us to acquire consequent amounts of good quality mono- and bilingual medical terminology data.