{"adoption": {"forks": 785, "observed_at": "2026-08-28T04:08:55.063099+00:00", "stars": 4612}, "canonical_url": "https://ross.abutalabs.com/products/insanelife-chinesenlpcorpus", "card": {"archived": false, "artifact_type": "dataset", "description": "中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。", "domain": ["machine-learning", "data-science", "chatbots"], "enriched": true, "function": ["nlp", "machine-learning", "data-science"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["InsaneLife/ChineseNLPCorpus"], "name": "InsaneLife/ChineseNLPCorpus", "platform": ["python", "cross-platform"], "pushed_at": "2023-11-21T12:33:51+00:00", "repo": "InsaneLife/ChineseNLPCorpus", "stars": 4612, "tags": ["chinese-nlp", "datasets", "reading-comprehension", "dialogue", "text-classification", "corpus-collection", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["find Chinese reading comprehension datasets like DuReader or CMRC 2018", "get Chinese medical dialogue data for task-oriented conversation research", "download Chinese NLP corpora for experiments", "find benchmark datasets for Chinese question answering", "locate Chinese text classification and sentiment datasets", "compare Chinese NLP datasets by size, source, and evaluation tasks"], "what_it_is": "A curated collection of Chinese natural language processing datasets, including reading comprehension, task-oriented dialogue, and other NLP corpora with links to papers, downloads, and benchmarks. It serves as a reference index for researchers and practitioners experimenting with Chinese NLP.", "when_to_avoid": ["you need English or multilingual datasets", "you need a software tool or library rather than data", "you need datasets with an active maintenance guarantee or license"], "when_to_choose": ["you need Chinese-language NLP training or evaluation data", "you are researching Chinese machine reading comprehension or dialogue systems", "you want a single index of Chinese NLP datasets with paper and download links"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/insanelife-chinesenlpcorpus", "repo": "InsaneLife/ChineseNLPCorpus", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.063099+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:19:42.292350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bc248bab9ff7a8f224771c95f954d82267bada350390b2300a30f72a1023c7dd", "fetched_at": "2026-08-28T04:08:55.063099+00:00", "kind": "readme", "missing": false, "url": "https://github.com/InsaneLife/ChineseNLPCorpus"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2832, "days_push": 1016, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}