{"url":"/task/native-language-identification","name":"Native Language Identification","slug":"native-language-identification","description_markdown":"Native Language Identification (NLI) is the task of determining an author's native language (L1) based only on their writings in a second language (L2).","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":83,"papers_with_code":5,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/native-language-identification-on-italki-nli","slug":"native-language-identification-on-italki-nli","dataset":"italki NLI","dataset_url":"/dataset/italki-nli","rows_in_archive":2,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"Tubasfs","paper_title":"Fewer features perform well at Native Language Identification task","paper_url":"/paper/fewer-features-perform-well-at-native","paper_date":"2017-09-01","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/italki-nli","name":"italki NLI","full_name":"italki NLI","num_papers_in_archive":3},{"url":"/dataset/nli-pt","name":"NLI-PT","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/language-identification","name":"Language Identification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":5,"of":5,"tagged_in_all":83,"items":[{"url":"/paper/native-language-identification-with-big-bird","title":"Native Language Identification with Big Bird Embeddings","date":"2023-09-13","arxiv_id":"2309.06923","repositories_listed":1,"syntology":null},{"url":"/paper/topics-to-avoid-demoting-latent-confounds-in","title":"Topics to Avoid: Demoting Latent Confounds in Text Classification","date":"2019-09-01","arxiv_id":"1909.00453","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ethical-content-based-detection-of","title":"Towards Ethical Content-Based Detection of Online Influence Campaigns","date":"2019-08-29","arxiv_id":"1908.11030","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-development-of-a-large-scale-corpus","title":"On the Development of a Large Scale Corpus for Native Language Identification","date":"2018-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-n-gram-and-embedding","title":"A study of N-gram and Embedding Representations for Native Language Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}