arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1307.1872cs.CL
收藏

智能混合人机机器翻译质量评估

Intelligent Hybrid Man-Machine Translation Quality Estimation

Alexandria University(亚历山大大学);Microsoft Research(微软研究院)

Ibrahim Sabek, Noha A. Yousri, Nagwa Elmakky, Mona Habib

摘要:

与使用不适合实时应用(例如,后期编辑)的当前评估度量相比,基于人类判断推断评估分数是非常宝贵的。然而,与基于对比源文本和翻译文本的指标的评估相比,这些判断的收集成本要高得多,特别是从专家翻译人员那里收集。这项工作介绍了一种新的方法,质量估计相结合的概率推理模型的基础上人类的判断,选择性的语言特征为基础的分数,其中建议的推理模型推断的可信度,以解决人类判断的稀缺性和不一致的问题。实验结果,使用具有挑战性的语言对,表现出改善与人类的判断,传统的评价指标。

英文摘要:

Inferring evaluation scores based on human judgments is invaluable compared to using current evaluation metrics which are not suitable for real-time applications e.g. post-editing. However, these judgments are much more expensive to collect especially from expert translators, compared to evaluation based on indicators contrasting source and translation texts. This work introduces a novel approach for quality estimation by combining learnt confidence scores from a probabilistic inference model based on human judgments, with selective linguistic features-based scores, where the proposed inference model infers the credibility of given human ranks to solve the scarcity and inconsistency issues of human judgments. Experimental results, using challenging language-pairs, demonstrate improvement in correlation with human judgments over traditional evaluation metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑