Dataset Groups Activity Stream MS MARCO dataset The MS MARCO dataset is a large-scale dataset for natural language understanding and question answering. BibTex: @dataset{Bhaskar_Mitra_and_Fernando_Diaz_and_Nick_Craswell_and_Li_Deng_and_Jianfeng_Gao_and_Xiaodong_Liu_and_Rangan_Majumder_and_Andrew_McNamara_and_Tri_Nguyen_2024, abstract = {The MS MARCO dataset is a large-scale dataset for natural language understanding and question answering.}, author = {Bhaskar Mitra and Fernando Diaz and Nick Craswell and Li Deng and Jianfeng Gao and Xiaodong Liu and Rangan Majumder and Andrew McNamara and Tri Nguyen}, doi = {10.57702/rgdh9tv1}, institution = {No Organization}, keyword = {'bias-sensitive', 'natural language understanding', 'passage ranking', 'passage retrieval', 'query-based', 'question answering'}, month = {dec}, publisher = {TIB}, title = {MS MARCO dataset}, url = {https://service.tib.eu/ldmservice/dataset/ms-marco-dataset}, year = {2024} }