Enhanced Bilingual Evaluation Understudy
2014-09-02 13:02:28 来源: 评论:0 点击:
Abstract—Our research extends the Bilingual Evaluation Understudy (BLEU) evaluation technique for statistical machine translation to make it more adjustable and robust. We intend to adapt it to resemble human evaluation more. We perform experiments to evaluate the performance of our technique against the primary existing evaluation methods. We describe and show the improvements it makes over existing methods as well as correlation to them. When human translators translate a text, they often use synonyms, different word orders or style, and other similar variations. We propose an SMT evaluation technique that enhances the BLEU metric to consider variations such as those.
Index Terms—machine translation, statistical machine translation, NLP, translation evaluation
Cite: Krzysztof Wołk and Krzysztof Marasek, "Enhanced Bilingual Evaluation Understudy," Lecture Notes on Information Theory, Vol. 2, No. 2, pp. 191-197, June 2014. doi: 10.12720/lnit.2.2.191-197
Index Terms—machine translation, statistical machine translation, NLP, translation evaluation
Cite: Krzysztof Wołk and Krzysztof Marasek, "Enhanced Bilingual Evaluation Understudy," Lecture Notes on Information Theory, Vol. 2, No. 2, pp. 191-197, June 2014. doi: 10.12720/lnit.2.2.191-197
Array
相关热词搜索:
上一篇:Prediction of Accident by Using Decision Tree and Display Accident Information
下一篇:Challenging of Path Planning Algorithms for Autonomous Robot in Unknown Environment
分享到:
收藏
评论排行
频道总排行
频道本月排行
- 22-Leyer Security System for Hi...
- 2Approach of Message Communicati...
- 1An Efficient Handover Predictio...
- 1Reduced Search Iterative Detect...
- 1Distribution Network Fault Loca...
- 1Estimating Resource Distribution...
- 1Aircraft Component Detection Ba...
- 1Fibonacci Based Text Hiding Using Image Cryptography
- 1Hierarchy Construction of Mathematical Knowledge
- 0Optimization of Location Aware...