Ahmed El-Kishky, Vishrav Chaudhary, Francisco Guzmán, Philipp Koehn. CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs. In Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu, editors, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020. pages 5960-5969, Association for Computational Linguistics, 2020. [doi]
@inproceedings{El-KishkyCGK20, title = {CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs}, author = {Ahmed El-Kishky and Vishrav Chaudhary and Francisco Guzmán and Philipp Koehn}, year = {2020}, url = {https://www.aclweb.org/anthology/2020.emnlp-main.480/}, researchr = {https://researchr.org/publication/El-KishkyCGK20}, cites = {0}, citedby = {0}, pages = {5960-5969}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020}, editor = {Bonnie Webber and Trevor Cohn and Yulan He and Yang Liu}, publisher = {Association for Computational Linguistics}, isbn = {978-1-952148-60-6}, }