Learning translation templates from examples


Creative Commons License

GUVENIR H., Cicekli I.

INFORMATION SYSTEMS, cilt.23, sa.6, ss.353-363, 1998 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 23 Sayı: 6
  • Basım Tarihi: 1998
  • Doi Numarası: 10.1016/s0306-4379(98)00017-9
  • Dergi Adı: INFORMATION SYSTEMS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.353-363
  • Hacettepe Üniversitesi Adresli: Hayır

Özet

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.