An effective way to reveal the contents of researchpapers is assigning a group of terms against a controlledvocabulary. To the best of our knowledge, a variety ofautomatic indexing techniques have been studied to enhancethe effectiveness and the efficiency. However, the currentapproaches depended on the content of a research paper,such as title, abstract, etc., which suffering from limitationson the automatic indexing performance. In this paper, wepropose a new approach of automatic indexing for singleresearch paper with its references based on GeneticAlgorithm (GA). The extensive experiments on four subjectsshow the effectiveness of the proposed approach.
展开▼