@inproceedings{L16-1529,
 abstract = {In Sorani Kurdish, one of the most useful orthographic features in named-entity recognition -- capitalization -- is absent, as the language's Perso-Arabic script does not make a distinction between uppercase and lowercase letters. We describe a system for deriving an inferred capitalization value from closely related languages by phonological similarity, and illustrate the system using several related Western Iranian languages.
},
 address = {Portorož, Slovenia},
 author = {Patrick Littell and David R. Mortensen and Kartik Goyal and Chris Dyer and Lori Levin},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {3318--3324},
 publisher = {European Language Resources Association (ELRA)},
 title = {Bridge-Language Capitalization Inference in Western Iranian: Sorani, Kurmanji, Zazaki, and Tajik},
 url = {https://www.aclweb.org/anthology/L16-1529},
 year = {2016}
}

