Improving term candidates selection using terminological tokens

Abstract The identification of reliable terms from domain-specific corpora using computational methods is a task that has to be validated manually by specialists, which highly time-consuming activity. To reduce this effort and improve term candidate selection, we implemented the Token Slot Recognition method, filtering method based on terminological tokens used rank extracted candidates corpora. This paper presents implementation developed in linguistic statistical approaches applied for automatic extraction several different languages. We observed outperforms selection ranking higher number at top list than raw frequency, improvement between 15% 25% both precision recall. Our analyses further revealed reduction specialists. In conclusion, automatically been reduced significantly so can easily quickly