{"adoption": {"forks": 2267, "observed_at": "2026-08-28T04:09:44.872256+00:00", "stars": 6517}, "canonical_url": "https://ross.abutalabs.com/products/ansj_seg", "card": {"archived": false, "artifact_type": "library", "description": "ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典", "domain": ["localization"], "enriched": true, "function": ["nlp", "parser"], "health_score": 20, "homepage": null, "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["NLPchina/ansj_seg"], "name": "NLPchina/ansj_seg", "platform": ["jvm"], "pushed_at": "2023-11-19T06:15:23+00:00", "repo": "NLPchina/ansj_seg", "stars": 6517, "tags": ["chinese-word-segmentation", "part-of-speech-tagging", "named-entity-recognition", "custom-dictionary", "keyword-extraction", "text-summarization", "natural-language-processing"], "topics": ["nlp", "chinese", "ansj", "java"], "urls": [], "use_cases": ["segment chinese text into words", "tokenize chinese sentences in java", "recognize chinese person names in text", "add custom domain dictionary to a chinese tokenizer", "extract keywords from chinese documents", "generate automatic summaries of chinese text", "tag parts of speech for chinese words"], "what_it_is": "A Java library for Chinese word segmentation based on n-Gram+CRF+HMM, achieving ~2 million characters/second with 96%+ accuracy. It also provides Chinese name recognition, part-of-speech tagging, custom dictionaries, keyword extraction, and automatic summarization.", "when_to_avoid": ["you need segmentation for languages other than chinese", "you want state-of-the-art neural (LSTM/transformer) segmentation models", "you need a library with frequent updates and active community support"], "when_to_choose": ["you need fast, high-accuracy chinese word segmentation on the JVM", "you want user-defined dictionaries and name recognition out of the box", "your project is Java/Maven-based and needs a pure-Java ict-class segmentation solution"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ansj_seg", "repo": "NLPchina/ansj_seg", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:44.872256+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:44:25.933012+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "878c96754bdf7e34a8f2c620d6808d825717061b3df092d1aa4c6821516e7193", "fetched_at": "2026-08-28T04:09:44.872256+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NLPchina/ansj_seg"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 5110, "days_push": 1018, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}