{"adoption": {"forks": 1422, "observed_at": "2026-08-28T04:09:45.562324+00:00", "stars": 6594}, "canonical_url": "https://ross.abutalabs.com/products/chinesenlpcorpus", "card": {"archived": false, "artifact_type": "dataset", "description": "搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "machine-learning", "data-science"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["SophonPlus/ChineseNlpCorpus"], "name": "SophonPlus/ChineseNlpCorpus", "platform": ["cross-platform"], "pushed_at": "2019-01-29T11:21:37+00:00", "repo": "SophonPlus/ChineseNlpCorpus", "stars": 6594, "tags": ["chinese-nlp", "corpus", "sentiment-analysis", "named-entity-recognition", "question-answering", "recommendation-systems", "text-classification", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["find chinese sentiment analysis datasets", "download chinese named entity recognition training data", "get chinese question answering corpus for chatbot training", "find chinese review data for text classification", "obtain chinese recommendation system datasets", "train chinese nlp models on public corpora"], "what_it_is": "A curated collection of Chinese natural language processing corpora and datasets, including sentiment analysis reviews, named entity recognition annotations, recommendation system ratings, and FAQ question-answering data. It serves as a central hub for downloading and exploring Chinese NLP datasets with introductory notebooks for each.", "when_to_avoid": ["you need datasets in languages other than Chinese", "you need actively maintained datasets with guaranteed updates or a formal license", "you need English NLP corpora"], "when_to_choose": ["you need labeled Chinese text data for sentiment analysis or NER", "you are building or benchmarking Chinese NLP models", "you want FAQ-style question answering data in Chinese domains like finance or law"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chinesenlpcorpus", "repo": "SophonPlus/ChineseNlpCorpus", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:45.562324+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/ChineseNlpCorpus"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:43:33.160688+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b1bae6d5f60016f04b20b6589a757e317c4d255074e87354fdb819809cbc9e6f", "fetched_at": "2026-08-28T04:09:45.562324+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SophonPlus/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": 3084, "days_push": 2773, "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}}