@inproceedings{a91e9b8064984101b75e3698136cbfd9,
title = "Orthographic and Morphological Processing for Persian-to-English Statistical Machine Translation",
abstract = "In statistical machine translation, data sparsity is a challenging problem especially for languages with rich morphology and inconsistent orthography, such as Persian. We show that orthographic preprocessing and morphological segmentation of Persian verbs in particular improves the translation quality of Persian-English by 1.9 BLEU points on a blind test set.",
author = "Rasooli, {Mohammad Sadegh} and Kholy, {Ahmed El} and Nizar Habash",
note = "Funding Information: Acknowledgments The second author was funded by a research grant from the Science Applications International Corporation (SAIC). We thank Nadi Tomeh for helpful discussions. Publisher Copyright: {\textcopyright} IJCNLP 2013.All right reserved.; 6th International Joint Conference on Natural Language Processing, IJCNLP 2013 ; Conference date: 14-10-2013",
year = "2013",
language = "English (US)",
series = "6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference",
publisher = "Asian Federation of Natural Language Processing",
pages = "1047--1051",
editor = "Ruslan Mitkov and Park, {Jong C.}",
booktitle = "6th International Joint Conference on Natural Language Processing, IJCNLP 2013 - Proceedings of the Main Conference",
}