Mitigating Problems in Analogy-based EBMT with SMT and vice versa: A Case Study with Named Entity Transliteration
Mitigating Problems in Analogy-based EBMT with SMT and vice versa: A Case Study with Named Entity Transliteration
复制标题
使用 SMT 缓解基于类比的 EBMT 中的问题，反之亦然：命名实体音译的案例研究
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
H. Somers
中科院分区：
文献类型：
--
作者：
Sandipan Dandapat;Sara Morrissey;S. Naskar;H. Somers
五年前，一些论文报道了使用比例类比的基于示例的机器翻译（EBMT）系统的实验实现。这种方法是一种类比学习，由于其简单而具有吸引力;该论文报告了使用各种语言对的方法取得的相当大的成功。在本文中，我们描述了我们试图使用这种方法来解决英语印地语命名实体（NE）音译。我们已经实现了我们自己的EBMT系统，使用比例类比，并发现基于类比的系统本身具有低精度，但高召回率，由于大量的名字是untransliterated的方法。然而，缓解问题的模拟为基础的EBMT与SMT，反之亦然，已经显示出相当大的改善，个别的方法。
Five years ago, a number of papers reported an experimental implementation of an Example Based Machine Translation (EBMT) system using proportional analogy. This approach, a type of analogical learning, was attractive because of its simplicity; and the paper reported considerable success with the method using various language pairs. In this paper, we describe our attempt to use this approach for tackling English-Hindi Named Entity (NE) Transliteration. We have implemented our own EBMT system using proportional analogy and have found that the analogy-based system on its own has low precision but a high recall due to the fact that a large number of names are untransliterated with the approach. However, mitigating problems in analogy-based EBMT with SMT and vice-versa have shown considerable improvement over the individual approach.