【作者】 曹冬林； 李堂秋； 史晓东； 蔡经球；

【Author】 CAO Dong-lin LI Tang-qiu SHI Xiao-dong CAI Jing-qiu Computer Science Department of Xiamen University Xiamen 361005

【机构】 厦门大学计算机科学系；

【摘要】 机器翻译是人工智能领域中一项有挑战性的研究课题,而对机器翻译系统的测评也越来越受到重视。但机器翻译测评往往忽略了测评结果的一致性。为了定量地分析测评结果的一致性,本文提出了采用计算数据前后的变化趋势的方法,对测评结果进行一致性分析,从而说明测评结果的客观性和公正性。更多还原

【Abstract】 Machine Translation is one of the most challenging problems in artificial intelligence and recently its evaluation gets more and more attention. But most evaluation of machine translation has lost sight of the consistency of evaluation result. In order to give a quantitative analysis to the consistency of evaluation result, this paper presents a method of calculating the direction of data change. We have used it to analyse the consistency of our evaluation result and prove the objectivity and notarization.更多还原