Dataset Groups Activity Stream How2: A large-scale dataset for multimodal language understanding A large-scale multimodal machine translation dataset named How2, which has 1.57 times longer mean sentence length than Multi30k and no repetition. BibTex: @dataset{Vikas_Raunak_and_Sang_Keun_Choe_and_Quanyang_Lu_and_Yi_Xu_and_Florian_Metze_2024, abstract = {A large-scale multimodal machine translation dataset named How2, which has 1.57 times longer mean sentence length than Multi30k and no repetition.}, author = {Vikas Raunak and Sang Keun Choe and Quanyang Lu and Yi Xu and Florian Metze}, doi = {10.57702/n0cwczp9}, institution = {No Organization}, keyword = {'How2 dataset', 'large-scale dataset', 'multimodal machine translation'}, month = {dec}, publisher = {TIB}, title = {How2: A large-scale dataset for multimodal language understanding}, url = {https://service.tib.eu/ldmservice/dataset/how2--a-large-scale-dataset-for-multimodal-language-understanding}, year = {2024} }
