English-Turkish Parallel Treebank with Morphological Annotations and its Use in Tree-based SMT

Onur Görgün, Olcay Taner Yıldız, Ercan Solak, Razieh Ehsani

2016

Abstract

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.

Paper Citation

in Harvard Style

Görgün O., Yıldız O., Solak E. and Ehsani R. (2016). English-Turkish Parallel Treebank with Morphological Annotations and its Use in Tree-based SMT . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 510-516. DOI: 10.5220/0005653905100516

in Bibtex Style

@conference{icpram16,
author={Onur Görgün and Olcay Taner Yıldız and Ercan Solak and Razieh Ehsani},
title={English-Turkish Parallel Treebank with Morphological Annotations and its Use in Tree-based SMT},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={510-516},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005653905100516},
isbn={978-989-758-173-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - English-Turkish Parallel Treebank with Morphological Annotations and its Use in Tree-based SMT
SN - 978-989-758-173-1
AU - Görgün O.
AU - Yıldız O.
AU - Solak E.
AU - Ehsani R.
PY - 2016
SP - 510
EP - 516
DO - 10.5220/0005653905100516