{"adoption": {"forks": 312, "observed_at": "2026-08-28T04:05:17.007453+00:00", "stars": 1652}, "canonical_url": "https://ross.abutalabs.com/products/eda_nlp", "card": {"archived": false, "artifact_type": "library", "description": "Data augmentation for NLP, presented at EMNLP 2019", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "data-generation", "machine-learning"], "health_score": 20, "homepage": "https://arxiv.org/abs/1901.11196", "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["jasonwei20/eda_nlp"], "name": "jasonwei20/eda_nlp", "platform": ["python", "cli"], "pushed_at": "2023-03-19T21:39:48+00:00", "repo": "jasonwei20/eda_nlp", "stars": 1652, "tags": ["data-augmentation", "text-classification", "synonym-replacement", "wordnet", "nltk", "research-code", "emnlp-2019", "natural-language-processing"], "topics": ["nlp", "data-augmentation", "text-classification", "synonyms", "embeddings", "sentence", "classification", "rnn", "cnn", "swap", "position"], "urls": [], "use_cases": ["augment a small text classification dataset", "generate synthetic training sentences via synonym replacement", "improve classifier accuracy with limited labeled data", "apply random swap and deletion augmentation to NLP training data", "replicate EMNLP 2019 EDA paper experiments"], "what_it_is": "EDA (Easy Data Augmentation) is a Python library implementing four simple text augmentation operations—synonym replacement, random insertion, random swap, and random deletion—for boosting text classification performance. It is the official code for an EMNLP 2019 paper and works especially well on small training datasets.", "when_to_avoid": ["you need augmentation for languages other than English without extra work", "you want context-aware or LLM-based paraphrasing quality", "you need a maintained, licensed production dependency (no license, minimal upkeep)"], "when_to_choose": ["you have a small text classification dataset (under ~500 examples) and need more training data", "you want lightweight augmentation without training a language model", "you need a simple, well-cited baseline augmentation technique"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/eda_nlp", "repo": "jasonwei20/eda_nlp", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:17.007453+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:45:00.350715+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "12566a722c76ee985492e50fcb6279e58c0709aecc7f7dc5a4ade30cb69c169a", "fetched_at": "2026-08-28T04:05:17.007453+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jasonwei20/eda_nlp"}, {"content_hash": "0bbc7f7929f7e7d4af6b7e9ccb09d37ac8d332d7380fdd2a18f928509898d3ab", "fetched_at": "2026-08-29T11:18:13.706183+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1901.11196"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:18:13.715552+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:18:13.719194+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:18:13.721223+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:18:13.717440+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2807, "days_push": 1263, "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}}