Dataset Groups Activity Stream STS benchmark The STS benchmark dataset contains 8,628 sentence pairs from the categories of captions, news, and forums. BibTex: @dataset{Eneko_Agirre_and_Carmen_Banea_and_Claire_Cardie_and_Daniel_Cer_and_Mona_Diab_and_Aitor_Gonzalez-Agirre_and_Weiwei_Guo_and_Rada_Mihalcea_2024, abstract = {The STS benchmark dataset contains 8,628 sentence pairs from the categories of captions, news, and forums.}, author = {Eneko Agirre and Carmen Banea and Claire Cardie and Daniel Cer and Mona Diab and Aitor Gonzalez-Agirre and Weiwei Guo and Rada Mihalcea}, doi = {10.57702/jzu7sdnx}, institution = {No Organization}, keyword = {'semantic textual similarity', 'sentence embeddings'}, month = {dec}, publisher = {TIB}, title = {STS benchmark}, url = {https://service.tib.eu/ldmservice/dataset/sts-benchmark}, year = {2024} }
