@inproceedings{xu-koehn-2017-zipporah, title = "{Z}ipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora", author = "Xu, Hainan and Koehn, Philipp", editor = "Palmer, Martha and Hwa, Rebecca and Riedel, Sebastian", booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D17-1319/", doi = "10.18653/v1/D17-1319", pages = "2945--2950" }