{"adoption": {"forks": 956, "observed_at": "2026-08-28T04:10:08.336803+00:00", "stars": 7867}, "canonical_url": "https://ross.abutalabs.com/products/stanza", "card": {"archived": false, "artifact_type": "library", "description": "Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages", "domain": ["machine-learning", "artificial-intelligence"], "enriched": true, "function": ["nlp", "machine-learning", "deep-learning", "parser"], "health_score": 100, "homepage": "https://stanfordnlp.github.io/stanza/", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "stable", "member_repos": ["stanfordnlp/stanza"], "name": "stanfordnlp/stanza", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T23:51:55+00:00", "repo": "stanfordnlp/stanza", "stars": 7867, "tags": ["pytorch", "named-entity-recognition", "universal-dependencies", "tokenization", "dependency-parsing", "corenlp", "biomedical-nlp", "multilingual", "natural-language-processing", "gpu"], "topics": ["python", "nlp", "natural-language-processing", "machine-learning", "deep-learning", "artificial-intelligence", "pytorch", "universal-dependencies", "named-entity-recognition", "corenlp"], "urls": [], "use_cases": ["tokenize and segment sentences in many languages", "run named entity recognition on text", "get dependency parses in Universal Dependencies format", "tag parts of speech and morphological features", "extract entities from biomedical literature and clinical notes", "access CoreNLP features like coreference resolution from Python", "train custom NLP models on annotated data"], "what_it_is": "Stanza is the Stanford NLP Group's official Python library for linguistic analysis of human language text. It provides a neural pipeline built on PyTorch for tokenization, sentence segmentation, lemmatization, POS tagging, dependency parsing, and named entity recognition across 70+ languages, plus a Python interface to Java CoreNLP.", "when_to_avoid": ["you need fast CPU-only inference for high-throughput production (GPU recommended)", "you want a lightweight rule-based toolkit rather than neural models", "you need tasks like question answering or text generation"], "when_to_choose": ["you need accurate multilingual NLP with pretrained models for 70+ languages", "you want a native Python pipeline without a Java dependency", "you need Universal Dependencies-compliant tokenization and parsing", "you need biomedical/clinical NER models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/stanza", "repo": "stanfordnlp/stanza", "role": "main", "score": 97}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:08.336803+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:33:45.383171+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ff5ca563671cc548a57866c7a03fd60c78bef44dcd2e07fc40284f8c87084d91", "fetched_at": "2026-08-28T04:10:08.336803+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanfordnlp/stanza"}, {"content_hash": "90ab68be0cd15e1092abc1418df021dd474871eddb7b3c7c895161947c6dd9b2", "fetched_at": "2026-08-29T08:30:12.981198+00:00", "kind": "homepage", "missing": false, "url": "https://stanfordnlp.github.io/stanza/"}, {"content_hash": "734c7c690ce1aa35c41d32bf98f724f31fe1db91674e06a3c8bb6a43f96717dc", "fetched_at": "2026-08-29T08:30:12.983807+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/stanza/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 93}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3263, "days_push": 7, "days_rel": 50, "gap_med": 14, "n_releases_24m": 12}, "score": 97, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}