NAIST-NTT System Description for Patent Translation Task at NTCIR-7

NAIST-NTT System Description for Patent Translation Task at NTCIR-7
复制标题

DOI:
--
复制
发表时间:
2008
期刊:
--
影响因子:
--
通讯作者:
Mamoru Komachi;M. Nagata;Yuji Matsumoto
Mamoru Komachi;M. Nagata;Yuji Matsumoto
中科院分区:
其他
文献类型:
--
作者:
Mamoru Komachi;M. Nagata;Yuji Matsumoto

文献摘要

相似文献

本文提出了一种从维基百科集合中获取特定领域翻译知识的半监督方法。该方法从给定语料库中每个领域的少量种子翻译对开始,利用正则化的拉普拉斯算子学习与该领域相关的翻译对。本文给出了使用NTCIR-7专利翻译任务的评估结果。
This paper proposes a semi-supervised approach to acquire domain specific translation knowledge from the collection of Wikipedia. The proposed method starts from a small number of seed translation pairs for each domain in a given corpus, and applies the regularized Laplacian to learn translation pairs relevant to the domain. This paper presents evaluation results using the NTCIR-7 Patent Translation Task.