{"url":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","slug":"cross-lingual-transfer","description_markdown":"Cross-lingual transfer refers to transfer learning using data and models available for one language for which ample such resources are available (e.g., English) to solve tasks in another, commonly more low-resource, language.","categories":[{"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":782,"papers_with_code":333,"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":15,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/cross-lingual-transfer-on-xcopa","slug":"cross-lingual-transfer-on-xcopa","dataset":"XCOPA","dataset_url":"/dataset/xcopa","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLM 2 (few-shot)","paper_title":"PaLM 2 Technical Report","paper_url":"/paper/palm-2-technical-report-1","paper_date":"2023-05-17","arxiv_id":"2305.10403","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"syntology":null}}],"datasets":[{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/paws-x","name":"PAWS-X","full_name":"PAWS-X","num_papers_in_archive":172},{"url":"/dataset/mlqa","name":"MLQA","full_name":"MultiLingual Question Answering","num_papers_in_archive":167},{"url":"/dataset/cc100","name":"CC100","full_name":"","num_papers_in_archive":115},{"url":"/dataset/xcopa","name":"XCOPA","full_name":null,"num_papers_in_archive":110},{"url":"/dataset/wikiann-1","name":"WikiANN","full_name":"PAN-X","num_papers_in_archive":72},{"url":"/dataset/conll-2002","name":"CoNLL 2002","full_name":"","num_papers_in_archive":70},{"url":"/dataset/tatoeba","name":"Tatoeba","full_name":"Tatoeba","num_papers_in_archive":38},{"url":"/dataset/tydiqa-goldp","name":"TyDiQA-GoldP","full_name":"TyDiQA-GoldP","num_papers_in_archive":38},{"url":"/dataset/covost","name":"CoVoST","full_name":"","num_papers_in_archive":34},{"url":"/dataset/jesc","name":"JESC","full_name":"Japanese-English Subtitle Corpus","num_papers_in_archive":17},{"url":"/dataset/xl-wic","name":"XL-WiC","full_name":"","num_papers_in_archive":15},{"url":"/dataset/dane","name":"DaNE","full_name":"Danish Dependency Treebank","num_papers_in_archive":6},{"url":"/dataset/wikineural","name":"WikiNEuRal","full_name":"","num_papers_in_archive":6},{"url":"/dataset/esxnli","name":"esXNLI","full_name":null,"num_papers_in_archive":3}],"subtasks":[{"url":"/task/cross-lingual-ner","name":"Cross-Lingual NER"},{"url":"/task/zero-shot-cross-lingual-transfer","name":"Zero-Shot Cross-Lingual Transfer"}],"parent_tasks":[{"url":"/task/cross-lingual","name":"Cross-Lingual"}],"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":30,"of":333,"tagged_in_all":782,"items":[{"url":"/paper/unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","arxiv_id":"1911.02116","repositories_listed":35,"syntology":{"n":59,"n_ran":25,"n_unverified":34,"n_pointer_only":52}},{"url":"/paper/massively-multilingual-sentence-embeddings","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","date":"2018-12-26","arxiv_id":"1812.10464","repositories_listed":13,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/does-manipulating-tokenization-aid-cross","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","date":"2023-04-20","arxiv_id":"2304.10158","repositories_listed":6,"syntology":null},{"url":"/paper/towards-unsupervised-dense-information","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.09118","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/model-and-data-transfer-for-cross-lingual","title":"Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings","date":"2022-10-23","arxiv_id":"2210.12623","repositories_listed":4,"syntology":null},{"url":"/paper/mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08151","repositories_listed":4,"syntology":null},{"url":"/paper/infoxlm-an-information-theoretic-framework","title":"InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training","date":"2020-07-15","arxiv_id":"2007.07834","repositories_listed":4,"syntology":null},{"url":"/paper/xtreme-a-massively-multilingual-multi-task","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","date":"2020-03-24","arxiv_id":"2003.11080","repositories_listed":4,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/pushing-the-limits-of-low-resource","title":"Pushing the Limits of Low-Resource Morphological Inflection","date":"2019-08-16","arxiv_id":"1908.05838","repositories_listed":4,"syntology":null},{"url":"/paper/visually-grounded-reasoning-across-languages","title":"Visually Grounded Reasoning across Languages and Cultures","date":"2021-09-28","arxiv_id":"2109.13238","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/word-alignment-by-fine-tuning-embeddings-on","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","date":"2021-01-20","arxiv_id":"2101.08231","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mad-x-an-adapter-based-framework-for-multi","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","date":"2020-04-30","arxiv_id":"2005.00052","repositories_listed":3,"syntology":null},{"url":"/paper/end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","repositories_listed":3,"syntology":null},{"url":"/paper/dont-just-scratch-the-surface-enhancing-word","title":"Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja","date":"2019-08-25","arxiv_id":"1908.09282","repositories_listed":3,"syntology":null},{"url":"/paper/cross-lingual-transfer-of-multilingual-models","title":"Cross-lingual transfer of multilingual models on low resource African Languages","date":"2024-09-17","arxiv_id":"2409.10965","repositories_listed":2,"syntology":null},{"url":"/paper/soft-language-prompts-for-language-transfer","title":"Soft Language Prompts for Language Transfer","date":"2024-07-02","arxiv_id":"2407.02317","repositories_listed":2,"syntology":null},{"url":"/paper/vocabulary-expansion-for-low-resource-cross","title":"How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?","date":"2024-06-17","arxiv_id":"2406.11477","repositories_listed":2,"syntology":{"n":12,"n_ran":9,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/unibridge-a-unified-approach-to-cross-lingual-1","title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","date":"2024-06-14","arxiv_id":"2406.09717","repositories_listed":2,"syntology":null},{"url":"/paper/mind-your-language-a-multilingual-dataset-for","title":"MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendation","date":"2024-03-26","arxiv_id":"2403.17876","repositories_listed":2,"syntology":null},{"url":"/paper/sib-200-a-simple-inclusive-and-big-evaluation","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","date":"2023-09-14","arxiv_id":"2309.07445","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-belebele-benchmark-a-parallel-reading","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","date":"2023-08-31","arxiv_id":"2308.16884","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":6}},{"url":"/paper/mt4crossoie-multi-stage-tuning-for-cross","title":"MT4CrossOIE: Multi-stage Tuning for Cross-lingual Open Information Extraction","date":"2023-08-12","arxiv_id":"2308.06552","repositories_listed":2,"syntology":null},{"url":"/paper/scandeval-a-benchmark-for-scandinavian","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","date":"2023-04-03","arxiv_id":"2304.00906","repositories_listed":2,"syntology":null},{"url":"/paper/frustratingly-easy-label-projection-for-cross","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","date":"2022-11-28","arxiv_id":"2211.15613","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/prompt-tuning-can-be-much-better-than-fine","title":"Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models","date":"2022-10-22","arxiv_id":"2210.12360","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/an-empirical-study-on-cross-x-transfer-for","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","date":"2022-09-25","arxiv_id":"2209.12325","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-learning-with-multilingual-language","title":"Few-shot Learning with Multilingual Language Models","date":"2021-12-20","arxiv_id":"2112.10668","repositories_listed":2,"syntology":null},{"url":"/paper/when-is-bert-multilingual-isolating-crucial","title":"When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer","date":"2021-10-27","arxiv_id":"2110.14782","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/composable-sparse-fine-tuning-for-cross","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","date":"2021-10-14","arxiv_id":"2110.07560","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/k-wav2vec-2-0-automatic-speech-recognition","title":"K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables","date":"2021-10-11","arxiv_id":"2110.05172","repositories_listed":2,"syntology":null}],"syntology_records":13,"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"}}