{"adoption": {"forks": 1553, "observed_at": "2026-08-28T04:10:38.771423+00:00", "stars": 9908}, "canonical_url": "https://ross.abutalabs.com/products/nlp_chinese_corpus", "card": {"archived": false, "artifact_type": "dataset", "description": "大规模中文自然语言处理语料  Large Scale Chinese Corpus for NLP", "domain": ["machine-learning", "large-language-models"], "enriched": true, "function": ["nlp", "machine-learning", "data-science"], "health_score": 60, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["brightmart/nlp_chinese_corpus"], "name": "brightmart/nlp_chinese_corpus", "platform": ["python", "cross-platform"], "pushed_at": "2026-02-06T11:42:20+00:00", "repo": "brightmart/nlp_chinese_corpus", "stars": 9908, "tags": ["chinese-corpus", "chinese-nlp", "pretraining-data", "word2vec", "question-answering", "machine-translation", "text-classification", "wiki-corpus", "news-corpus", "natural-language-processing"], "topics": ["chinese-dataset", "chinese-corpus", "pretrain", "word2vec", "nlp", "bert", "language-model", "wiki", "news", "question-answering", "chinese", "corpus", "chinese-nlp", "dataset", "text-classification"], "urls": [], "use_cases": ["download large chinese corpus for pretraining", "train chinese word embeddings", "get chinese question-answering dataset", "find chinese-english parallel sentences for translation", "build chinese language model training data", "chinese text classification corpus"], "what_it_is": "A collection of large-scale Chinese NLP corpora including Wikipedia entries, news articles, encyclopedia Q&A, community Q&A, and Chinese-English translation pairs. It provides millions of cleaned text records in JSON format for pretraining language models, building word vectors, and other Chinese NLP tasks.", "when_to_avoid": ["you need non-Chinese language corpora", "you need continuously updated real-time data rather than static snapshots", "you need labeled task-specific datasets beyond QA and translation"], "when_to_choose": ["you need millions of Chinese text records for pretraining or word vectors", "you want ready-to-use JSON corpora for Chinese NLP research", "you need Chinese-English translation pairs at scale"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nlp_chinese_corpus", "repo": "brightmart/nlp_chinese_corpus", "role": "main", "score": 52}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:38.771423+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:20:19.452990+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc69af59ee7e663d9cfaa2963bf17fd53b2cab971fc08d317cb4e44a37f0fe3e", "fetched_at": "2026-08-28T04:10:38.771423+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brightmart/nlp_chinese_corpus"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 66, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2763, "days_push": 208, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 52, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}