TY - GEN
T1 - Improving Arabic diacritization through syntactic analysis
AU - Shahrour, Anas
AU - Khalifa, Salam
AU - Habash, Nizar
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - We present an approach to Arabic automatic diacritization that integrates syntactic analysis with morphological tagging through improving the prediction of case and state features. Our best system increases the accuracy of word diacritization by 2.5% absolute on all words, and 5.2% absolute on nominals over a state-of-theart baseline. Similar increases are shown on the full morphological analysis choice.
AB - We present an approach to Arabic automatic diacritization that integrates syntactic analysis with morphological tagging through improving the prediction of case and state features. Our best system increases the accuracy of word diacritization by 2.5% absolute on all words, and 5.2% absolute on nominals over a state-of-theart baseline. Similar increases are shown on the full morphological analysis choice.
UR - http://www.scopus.com/inward/record.url?scp=84959919319&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959919319&partnerID=8YFLogxK
U2 - 10.18653/v1/d15-1152
DO - 10.18653/v1/d15-1152
M3 - Conference contribution
AN - SCOPUS:84959919319
T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
SP - 1309
EP - 1315
BT - Conference Proceedings - EMNLP 2015
PB - Association for Computational Linguistics (ACL)
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Y2 - 17 September 2015 through 21 September 2015
ER -