Improving Machine Translation of English Relative Clauses with Automatic Text Simplification

Improving Machine Translation of English Relative Clauses with Automatic Text Simplification
复制标题

通过自动文本简化改进英语关系从句的机器翻译

DOI:
10.18653/v1/w18-7006
复制
发表时间:
2018
期刊:
Proceedings of the 1st Workshop on Automatic Text Adaptation (ATA)
影响因子:
--
通讯作者:
Maja Popovic
Maja Popovic
中科院分区:
--
文献类型:
--
作者:
Sanja Štajner;Maja Popovic

文献摘要

参考文献

被引文献

相似文献

本文探讨了使用自动句子简化作为英语关系从句神经机器翻译为语法复杂语言的预处理步骤。我们对英语到塞尔维亚语和英语到德语翻译的实验表明,这种方法可以减少技术性后期编辑 努力(后期编辑操作的数量) 获得正确的翻译。我们发现 可以实现更大的改进 更复杂的目标语言,以及 对于整体性能较低的 MT 系统。改进主要源于正确的简化句子 结构相对复杂,同时 更简单的结构已经被翻译了 充分利用原始来源 句子。
This article explores the use of automatic sentence simplification as a preprocessing step in neural machine translation of English relative clauses into grammatically complex languages. Our experiments on English-to-Serbian and English to-German translation show that this approach can reduce technical post-editing effort (number of post-edit operations) to obtain correct translation. We find that larger improvements can be achieved for more complex target languages, as well as for MT systems with lower overall performance. The improvements mainly originate from correctly simplified sentences with relatively complex structure, while simpler structures are already translated sufficiently well using the original source sentences.
DOI: 10.3115/v1/e14-1076
发表时间: 2014-04
期刊: --
影响因子: --
作者:
Advaith Siddharthan;Angrosh Mandya
通讯作者: Advaith Siddharthan;Angrosh Mandya