{"@context":{"@language":"en","@vocab":"https://schema.org/","arrayShape":"cr:arrayShape","citeAs":"cr:citeAs","column":"cr:column","conformsTo":"dct:conformsTo","cr":"http://mlcommons.org/croissant/","data":{"@id":"cr:data","@type":"@json"},"dataBiases":"cr:dataBiases","dataCollection":"cr:dataCollection","dataType":{"@id":"cr:dataType","@type":"@vocab"},"dct":"http://purl.org/dc/terms/","extract":"cr:extract","field":"cr:field","fileProperty":"cr:fileProperty","fileObject":"cr:fileObject","fileSet":"cr:fileSet","format":"cr:format","includes":"cr:includes","isArray":"cr:isArray","isLiveDataset":"cr:isLiveDataset","jsonPath":"cr:jsonPath","key":"cr:key","md5":"cr:md5","parentField":"cr:parentField","path":"cr:path","personalSensitiveInformation":"cr:personalSensitiveInformation","recordSet":"cr:recordSet","references":"cr:references","regex":"cr:regex","repeated":"cr:repeated","replace":"cr:replace","sc":"https://schema.org/","separator":"cr:separator","source":"cr:source","subField":"cr:subField","transform":"cr:transform"},"@type":"sc:Dataset","distribution":[{"@type":"cr:FileObject","@id":"repo","name":"repo","description":"The Hugging Face git repository.","contentUrl":"https://huggingface.co/datasets/QiyaoWei/Semantic-KG/tree/refs%2Fconvert%2Fparquet","encodingFormat":"git+https","sha256":"https://github.com/mlcommons/croissant/issues/80"},{"@type":"cr:FileSet","@id":"parquet-files-for-config-default","containedIn":{"@id":"repo"},"encodingFormat":"application/x-parquet","includes":"default/*/*.parquet"}],"recordSet":[{"@type":"cr:RecordSet","dataType":"cr:Split","key":{"@id":"default_splits/split_name"},"@id":"default_splits","name":"default_splits","description":"Splits for the default config.","field":[{"@type":"cr:Field","@id":"default_splits/split_name","dataType":"sc:Text"}],"data":[{"default_splits/split_name":"train"}]},{"@type":"cr:RecordSet","@id":"default","description":"QiyaoWei/Semantic-KG - 'default' subset","field":[{"@type":"cr:Field","@id":"default/split","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"fileProperty":"fullpath"},"transform":{"regex":"default/(?:partial-)?(train)/.+parquet$"}},"references":{"field":{"@id":"default_splits/split_name"}}},{"@type":"cr:Field","@id":"default/subgraph_triples","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"subgraph_triples"}}},{"@type":"cr:Field","@id":"default/perturbed_subgraph_triples","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"perturbed_subgraph_triples"}}},{"@type":"cr:Field","@id":"default/perturbation_log","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"perturbation_log"}}},{"@type":"cr:Field","@id":"default/similarity","dataType":"cr:Float64","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"similarity"}}},{"@type":"cr:Field","@id":"default/perturbation_type","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"perturbation_type"}}},{"@type":"cr:Field","@id":"default/split","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"split"}}},{"@type":"cr:Field","@id":"default/response1","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"response1"}}},{"@type":"cr:Field","@id":"default/response2","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"response2"}}},{"@type":"cr:Field","@id":"default/label","dataType":"cr:Int64","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"label"}}},{"@type":"cr:Field","@id":"default/dataset_name","dataType":"sc:Text","source":{"fileSet":{"@id":"parquet-files-for-config-default"},"extract":{"column":"dataset_name"}}}]}],"conformsTo":"http://mlcommons.org/croissant/1.1","name":"Semantic-KG","description":"\n\t\n\t\t\n\t\tDataset Card for Semantic-KG\n\t\n\nThis is a dataset for evaluating semantic similarity containing semantically similar and dissimilar natural language statement pairs generated from knowledge graphs across four domains: general knowledge, biomedicine, finance, and biology.\n\n\t\n\t\t\n\t\tDataset Details\n\t\n\n\n\t\n\t\t\n\t\tDataset Description\n\t\n\nThis dataset is designed to evaluate semantic-textual similarity (STS) methods across diverse domains. It is generated using the Semantic-KG framework, an… See the full description on the dataset page: https://huggingface.co/datasets/QiyaoWei/Semantic-KG.","alternateName":["QiyaoWei/Semantic-KG","Semantic-KG"],"creator":{"@type":"Person","name":"Qiyao Wei","url":"https://huggingface.co/QiyaoWei"},"keywords":["text-classification","English","1K - 10K","csv","Tabular","Text","Datasets","pandas","Croissant","Polars","🇺🇸 Region: US","medical","biology","finance","Synthetic"],"url":"https://huggingface.co/datasets/QiyaoWei/Semantic-KG"}