Cognate-aware morphological segmentation for multilingual neural translation
Cognate-aware morphological segmentation for multilingual neural translation
复制标题
用于多语言神经翻译的同源感知形态分割
DOI：
10.18653/v1/w18-6410
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
M. Kurimo
中科院分区：
文献类型：
--
作者：
Stig;Sami Virpioja;M. Kurimo
本文介绍了阿尔托大学进入WMT18新闻翻译共享任务。我们参与了多语言子轨道的系统训练下的约束条件下，从英语翻译到芬兰语和爱沙尼亚语。该系统基于Transformer模型。我们专注于提高的一致性形态分割的字是相似的正字法，语义和分布，这样的话，包括词源同源词，借词和专有名词。为此，我们引入同源Morfessor，Morfessor方法的多语言变体。我们表明，我们的方法提高了翻译质量，特别是对于爱沙尼亚语，它有较少的资源来训练翻译模型。
This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.