A tree-based approach for English-to-Turkish translation
Yükleniyor...
Dosyalar
Tarih
2019
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Tubitak Scientific & Technical Research Council Turkey
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
In this paper, we present our English-to-Turkish translation methodology, which adopts a tree-based approach. Our approach relies on tree analysis and the application of structural modification rules to get the target side (Turkish) trees from source side (English) ones. We also use morphological analysis to get candidate root words and apply tree-based rules to obtain the agglutinated target words. Compared to earlier work on English-to-Turkish translation using phrase-based models, we have been able to obtain higher BLEU scores in our current study. Our syntactic subtree permutation strategy, combined with a word replacement algorithm, provides a 67% relative improvement from a baseline 12.8 to 21.4 BLEU, all averaged over 10-fold cross-validation. As future work, improvements in choosing the correct senses and structural rules are needed.
Açıklama
Anahtar Kelimeler
Computer aided language translation, Computational linguistics, Hierarchical phrase-based, Computer science, 10-fold cross-validation, Morphological analysis, Phrase-based models, Replacement algorithm, Structural modifications, Structural rules, Target words, Tree-based approach
Kaynak
Turkish Journal of Electrical Engineering and Computer Sciences
WoS Q Değeri
Q4
Scopus Q Değeri
Q3
Cilt
27
Sayı
1
Künye
Bakay, O., Avar, B. & Yıldız, O. T. (2019). A tree-based approach for English-to-Turkish translation. Turkish Journal of Electrical Engineering and Computer Sciences, 27(1), 437-452. doi:10.3906/elk-1807-341
