%0 Conference Proceedings
%T Arabic Tweets Treebanking and Parsing: A Bootstrapping Approach
%A Albogamy, Fahad
%A Ramsay, Allan
%A Ahmed, Hanady
%Y Habash, Nizar
%Y Diab, Mona
%Y Darwish, Kareem
%Y El-Hajj, Wassim
%Y Al-Khalifa, Hend
%Y Bouamor, Houda
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Third Arabic Natural Language Processing Workshop
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F albogamy-etal-2017-arabic
%X In this paper, we propose using a “bootstrapping” method for constructing a dependency treebank of Arabic tweets. This method uses a rule-based parser to create a small treebank of one thousand Arabic tweets and a data-driven parser to create a larger treebank by using the small treebank as a seed training set. We are able to create a dependency treebank from unlabelled tweets without any manual intervention. Experiments results show that this method can improve the speed of training the parser and the accuracy of the resulting parsers.
%R 10.18653/v1/W17-1312
%U https://aclanthology.org/W17-1312
%U https://doi.org/10.18653/v1/W17-1312
%P 94-99