Dataset Groups Activity Stream OPUS-100 The dataset used in the paper is a subset of the OPUS-MT dataset, containing 1M randomly sampled examples from the OPUS-100 dataset. BibTex: @dataset{Kshitij_Gupta_2025, abstract = {The dataset used in the paper is a subset of the OPUS-MT dataset, containing 1M randomly sampled examples from the OPUS-100 dataset.}, author = {Kshitij Gupta}, doi = {10.57702/stcsmpqf}, institution = {No Organization}, keyword = {'GNOME Documentation', 'Machine Translation', 'Movie Subtitles', 'Multilingual', 'OPUS-100', 'Zero-Shot Translation', 'language pairs', 'machine translation', 'parallel corpus'}, month = {jan}, publisher = {TIB}, title = {OPUS-100}, url = {https://service.tib.eu/ldmservice/dataset/opus-100}, year = {2025} }
