Improving Term Extraction with Terminological Resources

Abstract. Studies of different term extractors on a corpus of the biomedical domain revealed decreasing performances when applied to highly technical texts. Facing the difficulty or impossibility to customize existing tools, we developed a tunable term extractor. It exploits linguistic-based rules in combination with the reuse of existing terminologies, i.e. exogenous disambiguation. Experiments reported here show that the combination of the two strategies allows the extraction of a greater number of term candidates with a higher level of reliability. We further describe the extraction process involving both endogenous and exogenous disambiguation implemented in the term extractor YATEA .

• Type: Conference
• Year: 2006
• Where: FINTAL
• Authors: Sophie Aubin, Thierry Hamon
• Keywords: Exogenous Disambiguation, FINTAL 2006, Natural Language Processing, Term Extractor, Tunable Term Extractor