{"url":"/sota/cross-lingual-document-classification-on","task":{"name":"Cross-Lingual Document Classification","url":"/task/cross-lingual-document-classification","note":null},"dataset":{"name":"MLDoc Zero-Shot English-to-German","url":"/dataset/mldoc"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Cross-lingual document classification refers to the task of using data and models available for one language for which ample such resources are available (e.g., English) to solve classification tasks in another, commonly low-resource, language.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":5,"rows_with_code":5,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"XLMft UDA","metrics":{"Accuracy":"96.95%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/bridging-the-domain-gap-in-cross-lingual","paper_url":"https://arxiv.org/abs/1909.07009v2","paper_title":"Bridging the domain gap in cross-lingual document classification","code":"https://github.com/laiguokun/xlu-data","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"MultiFiT, pseudo","metrics":{"Accuracy":"91.62%"},"uses_additional_data":false,"paper_date":"2019-09-10","paper":"/paper/multifit-efficient-multi-lingual-language","paper_url":"https://arxiv.org/abs/1909.04761v2","paper_title":"MultiFiT: Efficient Multi-lingual Language Model Fine-tuning","code":"https://github.com/piegu/language-models","n_code_links":4,"syntology":null},{"rank_in_archive_order":3,"model":"Massively Multilingual Sentence Embeddings","metrics":{"Accuracy":"84.78%"},"uses_additional_data":false,"paper_date":"2018-12-26","paper":"/paper/massively-multilingual-sentence-embeddings","paper_url":"https://arxiv.org/abs/1812.10464v2","paper_title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","code":"https://github.com/facebookresearch/LASER","n_code_links":13,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":4}},{"rank_in_archive_order":4,"model":"MultiCCA + CNN","metrics":{"Accuracy":"81.2%"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/a-corpus-for-multilingual-document","paper_url":"http://arxiv.org/abs/1805.09821v1","paper_title":"A Corpus for Multilingual Document Classification in Eight Languages","code":"https://github.com/n-waves/multifit","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":14,"n_samples":15,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"BiLSTM (Europarl)","metrics":{"Accuracy":"71.83%"},"uses_additional_data":false,"paper_date":"2018-05-24","paper":"/paper/a-corpus-for-multilingual-document","paper_url":"http://arxiv.org/abs/1805.09821v1","paper_title":"A Corpus for Multilingual Document Classification in Eight Languages","code":"https://github.com/n-waves/multifit","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":14,"n_samples":15,"n_pointer_only_licence":1}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":21,"n_samples":27,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":35,"n_samples":42,"n_pointer_only_licence":8,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}