Dataset Groups Activity Stream Samanantar dataset The Samanantar dataset containing 49.6 million sentence pairs between English and 11 Indian languages. BibTex: @dataset{Kshitij_Gupta_and_Devansh_Gautam_and_Radhika_Mamidi_2024, abstract = {The Samanantar dataset containing 49.6 million sentence pairs between English and 11 Indian languages.}, author = {Kshitij Gupta and Devansh Gautam and Radhika Mamidi}, doi = {10.57702/2mdzu6co}, institution = {No Organization}, keyword = {'Indian languages', 'Machine Translation', 'Samanantar'}, month = {dec}, publisher = {TIB}, title = {Samanantar dataset}, url = {https://service.tib.eu/ldmservice/dataset/samanantar-dataset}, year = {2024} }
