AUTOMATIC METHOD FOR PROCESSING PARALLEL CORPUS

Abstract

We consider a method for automatic processing of parallel corpus of Russian and Ukrainian languages to create translation dictionaries. Cache Intersystems technologies are used to analyze textual information. We consider the method of forming bilingual dictionaries based on the analysis of parallel cases using iKnow technology. The selected words are compared in identical sentences in different languages. iKnow identifies concepts and relationships between them in the text. Concepts in sentences are subject and additions. The connections between the concepts are verbs, verb forms.