@inproceedings{86a71543b042457ea371afee73034c27,
title = "Identifying the L1 of non-native writers: The CMU-Haifa system",
abstract = "We show that it is possible to learn to identify, with high accuracy, the native language of English test takers from the content of the essays they write. Our method uses standard text classification techniques based on multiclass logistic regression, combining individually weak indicators to predict the most probable native language from a set of 11 possibilities. We describe the various features used for classification, as well as the settings of the classifier that yielded the highest accuracy.",
author = "Yulia Tsvetkov and Naama Twitto and Nathan Schneider and Noam Ordan and Manaal Faruqui and Victor Chahuneau and Shuly Wintner and Chris Dyer",
note = "Funding Information: This research was supported by a grant from the Israeli Ministry of Science and Technology. Publisher Copyright: {\textcopyright} 2013 Association for Computational Linguistics.; 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013 ; Conference date: 13-06-2013",
year = "2013",
language = "American English",
series = "Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013",
publisher = "Association for Computational Linguistics (ACL)",
pages = "279--287",
editor = "Joel Tetreault and Jill Burstein and Claudia Leacock",
booktitle = "Proceedings of the 8th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2013",
address = "United States",
}