Ines Turki Khemakhem


2015

pdf bib
Arabic-English Semantic Word Class Alignment to Improve Statistical Machine Translation
Ines Turki Khemakhem | Salma Jamoussi | Abdelmajid Ben Hamadou
Proceedings of the International Conference Recent Advances in Natural Language Processing

2013

pdf bib
Integrating morpho-syntactic features in English-Arabic statistical machine translation
Ines Turki Khemakhem | Salma Jamoussi | Abdelmajid Ben Hamadou
Proceedings of the Second Workshop on Hybrid Approaches to Translation

2010

pdf bib
The MIRACL Arabic-English statistical machine translation system for IWSLT 2010
Ines Turki Khemakhem | Salma Jamoussi | Abdelmajid Ben Hamadou
Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper describes the MIRACL statistical Machine Translation system and the improvements that were developed during the IWSLT 2010 evaluation campaign. We participated to the Arabic to English BTEC tasks using a phrase-based statistical machine translation approach. In this paper, we first discuss some challenges in translating from Arabic to English and we explore various techniques to improve performances on a such task. Next, we present our solution for disambiguating the output of an Arabic morphological analyzer. In fact, The Arabic morphological analyzer used produces all possible morphological structures for each word, with an unique correct proposition. In this work we exploit the Arabic-English alignment to choose the correct segmented form and the correct morpho-syntactic features produced by our morphological analyzer.

pdf bib
Arabic morpho-syntactic feature disambiguation in a translation context
Ines Turki Khemakhem | Salma Jamoussi | Abdelmajid Ben Hamadou
Proceedings of the 4th Workshop on Syntax and Structure in Statistical Translation