TESLA: Translation Evaluation of Sentences with Linear-Programming-Based Analysis

TESLA: Translation Evaluation of Sentences with Linear-Programming-Based Analysis
复制标题

DOI:
--
复制
发表时间:
2010-07
期刊:
--
影响因子:
--
通讯作者:
Chang Liu;Daniel Dahlmeier;H. Ng
Chang Liu;Daniel Dahlmeier;H. Ng
中科院分区:
其他
文献类型:
--
作者:
Chang Liu;Daniel Dahlmeier;H. Ng

文献摘要

被引文献

相似文献

我们推出了 TESLA-M 和 TESLA,这两种新颖的自动机器翻译评估指标具有最先进的性能。 TESLA-M 建立在 METEOR 和 MaxSim 的成功基础上,但采用了更具表现力的线性编程框架。 TESLA 进一步利用并行文本来构建浅层语义表示。我们在 WMT 2009 共享评估任务上对两者进行了评估,结果表明它们在大多数任务中都优于所有参与系统。
We present TESLA-M and TESLA, two novel automatic machine translation evaluation metrics with state-of-the-art performances. TESLA-M builds on the success of METEOR and MaxSim, but employs a more expressive linear programming framework. TESLA further exploits parallel texts to build a shallow semantic representation. We evaluate both on the WMT 2009 shared evaluation task and show that they outperform all participating systems in most tasks.