Dataset Groups Activity Stream ArzEn parallel corpus The ArzEn parallel corpus consists of speech transcriptions gathered through informal interviews with bilingual Egyptian Arabic-English speakers, as well as their English translations. BibTex: @dataset{Marwa_Gaser_and_Manuel_Mager_and_Injy_Hamed_and_Nizar_Habash_and_Slim_Abdennadher_and_Ngoc_Thang_Vu_2024, abstract = {The ArzEn parallel corpus consists of speech transcriptions gathered through informal interviews with bilingual Egyptian Arabic-English speakers, as well as their English translations.}, author = {Marwa Gaser and Manuel Mager and Injy Hamed and Nizar Habash and Slim Abdennadher and Ngoc Thang Vu}, doi = {10.57702/i5pqcw9l}, institution = {No Organization}, keyword = {'Egyptian Arabic', 'English', 'code-switching', 'machine translation'}, month = {dec}, publisher = {TIB}, title = {ArzEn parallel corpus}, url = {https://service.tib.eu/ldmservice/dataset/arzen-parallel-corpus}, year = {2024} }
