{ "data_id": "45569", "name": "DBLP-QuAD", "exact_name": "DBLP-QuAD", "version": 1, "version_label": "1.1", "description": "DBLP-QuAD is a scholarly question answering dataset over the DBLP knowledge graph. The dataset can also be found at https:\/\/zenodo.org\/record\/7643971 and https:\/\/huggingface.co\/datasets\/awalesushil\/DBLP-QuAD. The paper can be found at https:\/\/arxiv.org\/abs\/2303.13351. The reference DBLP KG dump in .nt format can be found at https:\/\/zenodo.org\/record\/7638511.", "format": "arff", "uploader": "Debayan Banerjee", "uploader_id": 36230, "visibility": "public", "creator": "\"Debayan Banerjee, Sushil Awale, Chris Biemann, Ricardo Usbeck\"", "contributor": null, "date": "2023-06-14 10:09:46", "update_comment": null, "last_update": "2023-06-14 10:09:46", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22116553\/dataset", "default_target_attribute": "query", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "DBLP-QuAD", "DBLP-QuAD is a scholarly question answering dataset over the DBLP knowledge graph. The dataset can also be found at https:\/\/zenodo.org\/record\/7643971 and https:\/\/huggingface.co\/datasets\/awalesushil\/DBLP-QuAD. The paper can be found at https:\/\/arxiv.org\/abs\/2303.13351. The reference DBLP KG dump in .nt format can be found at https:\/\/zenodo.org\/record\/7638511. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 10000, "NumberOfFeatures": 10, "NumberOfClasses": 9999, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 2, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 1, "PercentageOfNumericFeatures": 0, "Dimensionality": 0.001, "PercentageOfSymbolicFeatures": 20, "MajorityClassPercentage": 0.02, "MajorityClassSize": 2, "MinorityClassPercentage": 0.01, "MinorityClassSize": 1, "NumberOfBinaryFeatures": 2, "PercentageOfBinaryFeatures": 20 }, "tags": [ { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Life Science" } ], "features": [ { "name": "query", "index": "4", "type": "string", "distinct": "9999", "missing": "0", "target": "1" }, { "name": "id", "index": "0", "type": "string", "distinct": "7000", "missing": "0" }, { "name": "query_type", "index": "1", "type": "string", "distinct": "10", "missing": "0" }, { "name": "question", "index": "2", "type": "string", "distinct": "10000", "missing": "0" }, { "name": "paraphrased_question", "index": "3", "type": "string", "distinct": "10000", "missing": "0" }, { "name": "template_id", "index": "5", "type": "string", "distinct": "95", "missing": "0" }, { "name": "entities", "index": "6", "type": "string", "distinct": "9973", "missing": "0" }, { "name": "relations", "index": "7", "type": "string", "distinct": "23", "missing": "0" }, { "name": "temporal", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "held_out", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }