English-Turkish parallel treebank with morphological annotations and its use in tree-based SMT
Yükleniyor...
Dosyalar
Tarih
2016
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
SciTePress
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
In this paper, we report our tree based statistical translation study from English to Turkish. We describe our data generation process and report the initial results of tree-based translation under a simple model. For corpus construction, we used the Penn Treebank in the English side. We manually translated about 5K trees from English to Turkish under grammar constraints with adaptations to accommodate the agglutinative nature of Turkish morphology. We used a permutation model for subtrees together with a word to word mapping. We report BLEU scores under simple choices of inference algorithms.
Açıklama
Anahtar Kelimeler
Machine translation, Tree-based translation, Inference engines, Pattern recognition, Corpus construction, Data generation, Inference algorithm, Machine translations, Simple modeling, Statistical translation, Tree-based, Tree-based smt, Trees (mathematics)
Kaynak
Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2016)
WoS Q Değeri
Scopus Q Değeri
N/A
Cilt
Sayı
Künye
Görgün, O., Yıldız, O. T., Solak, E. & Ehsani, R. (2016). English-turkish parallel treebank with morphological annotations and its use in tree-based SMT. Paper presented at the Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2016), 510-516. doi:10.5220/0005653905100516
