Dataset Groups Activity Stream Mr. TyDi The Mr. TyDi dataset is a multilingual dataset for dense retrieval, consisting of 100,000 passages and 1,000,000 queries. BibTex: @dataset{Xinyu_Zhang_and_Nandan_Thakur_and_Odunayo_Ogundepo_and_Ehsan_Kamalloo_and_David_Alfonso-Hermelo_and_Xiaoguang_Li_and_Qun_Liu_and_Mehdi_Rezagholizadeh_and_Jimmy_Lin_2024, abstract = {The Mr. TyDi dataset is a multilingual dataset for dense retrieval, consisting of 100,000 passages and 1,000,000 queries.}, author = {Xinyu Zhang and Nandan Thakur and Odunayo Ogundepo and Ehsan Kamalloo and David Alfonso-Hermelo and Xiaoguang Li and Qun Liu and Mehdi Rezagholizadeh and Jimmy Lin}, doi = {10.57702/o7nteut0}, institution = {No Organization}, keyword = {'Dataset', 'Dense Retrieval', 'Mr. TyDi'}, month = {dec}, publisher = {TIB}, title = {Mr. TyDi}, url = {https://service.tib.eu/ldmservice/dataset/mr--tydi}, year = {2024} }
