Research on Automatic Chinese Multi-word Term Extraction Based on Term Component

摘要

This paper presents an automatic Chinese multi-word term extraction method based on the unithood and the termhood measure. The unithood of the candidate term is measured by the strength of inner unity and marginal variety. Term component is taken into account to estimate the termhood. Inspired by the economical law of term generating, we propose two measures of a candidate term to be a true term: the first measure is based on domain speciality of term, and the second one is based on the similarity between a candidate and a template that contains structured information of terms. Experiments on I.T. domain and Medicine domain show that our method is effective and portable in different domains.