{"adoption": {"forks": 271, "observed_at": "2026-08-28T04:03:58.495369+00:00", "stars": 1202}, "canonical_url": "https://ross.abutalabs.com/products/autophrase", "card": {"archived": false, "artifact_type": "library", "description": "AutoPhrase: Automated Phrase Mining from Massive Text Corpora", "domain": ["data-science"], "enriched": true, "function": ["nlp", "parser", "data-science"], "health_score": 20, "homepage": null, "language": "C++", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["shangjingbo1226/AutoPhrase"], "name": "shangjingbo1226/AutoPhrase", "platform": ["cpp"], "pushed_at": "2022-01-27T15:16:36+00:00", "repo": "shangjingbo1226/AutoPhrase", "stars": 1202, "tags": ["phrase-mining", "quality-phrases", "text-mining", "multi-language", "lexicon-extraction", "natural-language-processing", "linux", "macos", "docker"], "topics": ["quality-phrases", "text-mining", "multi-language", "automatic", "phrase", "lexicon", "compound-words"], "urls": [], "use_cases": ["extract quality phrases from large text corpora", "mine compound words and multi-word expressions automatically", "build a domain phrase lexicon from raw documents", "segment text into phrases for downstream NLP tasks", "mine key phrases from Chinese or Spanish text", "preprocess corpora by identifying salient phrases"], "what_it_is": "AutoPhrase is a C++/Java tool for automated phrase mining that extracts quality phrases from massive text corpora with minimal human effort, leveraging existing knowledge bases for distant supervision. It supports multiple languages including English, Spanish, and Chinese with automatic language detection.", "when_to_avoid": ["you need a maintained library with active development and recent fixes", "you want a pure Python or pip-installable solution", "your corpus is small and simple keyword extraction would suffice"], "when_to_choose": []}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/autophrase", "repo": "shangjingbo1226/AutoPhrase", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.495369+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:20:37.888384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "46dd2723238d85cf822aa49e7d7d6f480b3c034c1ef724b10a6b7e4e992fa125", "fetched_at": "2026-08-28T04:03:58.495369+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shangjingbo1226/AutoPhrase"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3562, "days_push": 1679, "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}}