{"adoption": {"forks": 171, "observed_at": "2026-08-28T04:05:48.398826+00:00", "stars": 1878}, "canonical_url": "https://ross.abutalabs.com/products/nlpcda", "card": {"archived": false, "artifact_type": "library", "description": "一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "data-generation", "machine-learning"], "health_score": 27, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["425776024/nlpcda"], "name": "425776024/nlpcda", "platform": ["python", "cross-platform"], "pushed_at": "2025-03-18T08:26:13+00:00", "repo": "425776024/nlpcda", "stars": 1878, "tags": ["data-augmentation", "chinese-nlp", "eda", "bert", "ner", "text-generation", "simbert", "natural-language-processing"], "topics": ["nlp", "data-augmentation", "chinese-data-augmentation", "nlpcda", "chinese-eda"], "urls": [], "use_cases": ["augment chinese text training data for nlp models", "generate similar sentences with bert for data augmentation", "augment NER BIO labeled data", "improve model robustness against adversarial text perturbations", "synonym replacement for chinese corpus expansion", "create more training examples from a small chinese dataset"], "what_it_is": "nlpcda is a Python library for one-click Chinese NLP data augmentation. It provides techniques like random entity replacement, synonym substitution, homophone character swaps, character deletion, neighbor permutation, BIO-format NER augmentation, translation-based augmentation, and SimBERT-based similar sentence generation.", "when_to_avoid": ["you need data augmentation for non-Chinese languages", "you expect accuracy gains in pure leaderboard-score competitions without semantic variation", "you need production text processing rather than training-data generation"], "when_to_choose": ["you need Chinese-language text augmentation with semantic preservation", "you want multiple augmentation strategies (EDA, NER-aware, SimBERT) in one pip-installable package", "you are training BERT-style Chinese models and need more varied training data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nlpcda", "repo": "425776024/nlpcda", "role": "main", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:48.398826+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:14:38.698752+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ceb0d8b6e5b9ef42cb1a4d0767f2a623f9a7f3de9fbad581a8db3c723af3d17", "fetched_at": "2026-08-28T04:05:48.398826+00:00", "kind": "readme", "missing": false, "url": "https://github.com/425776024/nlpcda"}, {"content_hash": "8a95772d262d6e91dcc15ec26aedd414ea3f5410c86a1d0748af6f8c77151437", "fetched_at": "2026-08-29T10:53:21.250287+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlpcda/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 12, "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": 2439, "days_push": 533, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}