{"@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/vec-ai/struct-ir-qrels/tree/refs%2Fconvert%2Fparquet", "encodingFormat": "git+https", "sha256": "https://github.com/mlcommons/croissant/issues/80"}], "recordSet": [], "conformsTo": "http://mlcommons.org/croissant/1.1", "name": "struct-ir-qrels", "description": "\n\t\n\t\t\n\t\tSSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data\n\t\n\ngithub\nWe employ LLM-based automatic evaluation and build a large-scale semi-structured retrieval benchmark (SSRB) using LLM generation and filtering, containing 14M structured objects from 99 different schemas across 6 domains, along with 8,485 test queries that combine both exact and fuzzy matching conditions.\nThis repository contains the qrel data for SSRB, The corpus and query files please\u2026 See the full description on the dataset page: https://huggingface.co/datasets/vec-ai/struct-ir-qrels.", "alternateName": ["vec-ai/struct-ir-qrels"], "creator": {"@type": "Organization", "name": "Vector AI", "url": "https://huggingface.co/vec-ai"}, "keywords": ["text-retrieval", "apache-2.0", "\ud83c\uddfa\ud83c\uddf8 Region: US"], "license": "https://choosealicense.com/licenses/apache-2.0/", "url": "https://huggingface.co/datasets/vec-ai/struct-ir-qrels"}