{ "builder_name": "google_wellformed_query", "citation": "@misc{faruqui2018identifying,\n title={Identifying Well-formed Natural Language Questions},\n author={Manaal Faruqui and Dipanjan Das},\n year={2018},\n eprint={1808.09419},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n", "config_name": "default", "dataset_name": "google_wellformed_query", "dataset_size": 1230988, "description": "Google's query wellformedness dataset was created by crowdsourcing well-formedness annotations for 25,100 queries from the Paralex corpus. Every query was annotated by five raters each with 1/0 rating of whether or not the query is well-formed.\n", "download_checksums": { "https://raw.githubusercontent.com/google-research-datasets/query-wellformedness/master/train.tsv": { "num_bytes": 805818, "checksum": null }, "https://raw.githubusercontent.com/google-research-datasets/query-wellformedness/master/test.tsv": { "num_bytes": 178070, "checksum": null }, "https://raw.githubusercontent.com/google-research-datasets/query-wellformedness/master/dev.tsv": { "num_bytes": 173131, "checksum": null } }, "download_size": 1157019, "features": { "rating": { "dtype": "float32", "_type": "Value" }, "content": { "dtype": "string", "_type": "Value" } }, "homepage": "https://github.com/google-research-datasets/query-wellformedness", "license": "", "size_in_bytes": 2388007, "splits": { "train": { "name": "train", "num_bytes": 857383, "num_examples": 17500, "dataset_name": "google_wellformed_query" }, "test": { "name": "test", "num_bytes": 189499, "num_examples": 3850, "dataset_name": "google_wellformed_query" }, "validation": { "name": "validation", "num_bytes": 184106, "num_examples": 3750, "dataset_name": "google_wellformed_query" } }, "version": { "version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0 } }