A method to Chinese-Vietnamese bilingual metallurgy term extraction based on a pivot language

Abstract

To settle resource scarcity problem for Chinese-Vietnamese bilingual aligned corpus in metallurgy field, a method to Chinese-Vietnamese bilingual term extraction in metallurgy field based on a pivot language is proposed. Firstly, term-unit and term-hood features are selected and inputted to the trained CRFs model to identify and extract Chinese metallurgy terminology. Secondly, the phrase-based statistical machine translation model is used to generate the Chinese-English phrase table and English-Vietnamese phrase table. With the pivot mapping idea, A Chinese-Vietnamese phrase table will be inferred out through pivot English. Finally, the former extracted Chinese metallurgy terms are used to filter the Chinese-Vietnamese phrase table, a Chinese-Vietnamese bilingual metallurgy term base, therefore, will be built. Experiments show that the proposed method achieved an accuracy rate at 69.45%. The method, under the resource absence of Chinese-Vietnamese bilingual alignment corpus, is validated as an effective solution to the difficult problem for Chinese-Vietnamese bilingual metallurgy term extraction.