Learning translation templates from examples

被引：32

作者：

Guvenir, HA ^{[1
]}

Cicekli, I ^{[1
]}

机构：

[1] Bilkent Univ, Dept Comp Engn & Informat Sci, TR-06533 Ankara, Turkey

来源：

INFORMATION SYSTEMS | 1998年 / 23卷 / 06期

关键词：

machine learning; machine translation; translation templates;

D O I：

10.1016/S0306-4379(98)00017-9

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper proposes a mechanism for learning lexical level correspondences between two languages from a set of translated sentence pairs. The proposed mechanism is based on an analogical reasoning between two translation examples. Given two translation examples, the similar parts of the sentences in the source language must correspond to the similar parts of the sentences in the target language. Similarly, the different parts should correspond to the respective parts in the translated sentences. The correspondences between the similarities, and also differences are learned in the form of translation templates. The approach has been implemented and tested on a small training dataset and produced promising results for further investigation. (C) 1998 Elsevier Science Ltd. All rights reserved.

引用

页码：353 / 363

页数：11