TY - GEN
T1 - Rich morphology generation using statistical machine translation
AU - El Kholy, Ahmed
AU - Habash, Nizar
N1 - Publisher Copyright:
© 2012 The Association for Computational Linguistics.
PY - 2012
Y1 - 2012
N2 - We present an approach for generation of morphologically rich languages using statistical machine translation. Given a sequence of lemmas and any subset of morphological features, we produce the inflected word forms. Testing on Arabic, a morphologically rich language, our models can reach 92.1% accuracy starting only with lemmas, and 98.9% accuracy if all the gold features are provided.
AB - We present an approach for generation of morphologically rich languages using statistical machine translation. Given a sequence of lemmas and any subset of morphological features, we produce the inflected word forms. Testing on Arabic, a morphologically rich language, our models can reach 92.1% accuracy starting only with lemmas, and 98.9% accuracy if all the gold features are provided.
UR - http://www.scopus.com/inward/record.url?scp=84890445864&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84890445864&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84890445864
T3 - INLG 2012 - Proceedings of the 7th International Natural Language Generation Conference
SP - 90
EP - 94
BT - INLG 2012 - Proceedings of the 7th International Natural Language Generation Conference
PB - Association for Computational Linguistics (ACL)
T2 - 7th International Natural Language Generation Conference, INLG 2012
Y2 - 30 May 2012 through 1 June 2012
ER -