Title: Research on automatic translation quality evaluation technology without translation references for large-scale translations
Abstract: The traditional automatic translation quality evaluation method mainly focuses on the automatic translation results of machine,and compares with the translation references to evaluate the translation quality.This paper puts forward a multi-strategy based automatic translation quality evaluation method without translation references for large-scale translations.The method can check and identify errors in artificial translations for accuracy,fluency,adequacy,etc.without translation references.i.e.identifying the accuracy by language rule,the fluency by language model,and the adequacy by word alignment results and dictionary information.When the translation quality auxiliary examination system based on this method was applied to Million Patent Translation Project of the State Intellectual Property Office,compared with the test group not using this system,the test group using this system has higher translation quality and completion efficiency of final results.
Publication Year: 2012
Publication Date: 2012-01-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot