{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/model-and-data-transfer-for-cross-lingual","title":"Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings","arxiv_id":"2210.12623","date":"2022-10-23","proceeding":null,"authors":["Iker García-Ferrero","Rodrigo Agerri","German Rigau"],"abstract":"Zero-resource cross-lingual transfer approaches aim to apply supervised models from a source language to unlabelled target languages. In this paper we perform an in-depth study of the two main techniques employed so far for cross-lingual zero-resource sequence labelling, based either on data or model transfer. Although previous research has proposed translation and annotation projection (data-based cross-lingual transfer) as an effective technique for cross-lingual sequence labelling, in this paper we experimentally demonstrate that high capacity multilingual language models applied in a zero-shot (model-based cross-lingual transfer) setting consistently outperform data-based cross-lingual transfer approaches. A detailed analysis of our results suggests that this might be due to important differences in language use. More specifically, machine translation often generates a textual signal which is different to what the models are exposed to when using gold standard data, which affects both the fine-tuning and evaluation processes. Our results also indicate that data-based cross-lingual transfer approaches remain a competitive option when high-capacity multilingual language models are not available.","url_abs":"https://arxiv.org/abs/2210.12623v2","url_pdf":"https://arxiv.org/pdf/2210.12623v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"model-and-data-transfer-for-cross-lingual","repo_url":"https://github.com/ikergarcia1996/annotation-projection-app","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"model-and-data-transfer-for-cross-lingual","repo_url":"https://github.com/ikergarcia1996/easy-label-projection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"model-and-data-transfer-for-cross-lingual","repo_url":"https://github.com/ikergarcia1996/Easy-Translate","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"model-and-data-transfer-for-cross-lingual","repo_url":"https://github.com/ikergarcia1996/Iker-Garcia-Ferrero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-ner-on-conll-2003","task":"Cross-Lingual NER","dataset":"CoNLL 2003","model":"XLM-RoBERTa-large","rank_in_archive_order":1,"of":4,"metrics":{"Dutch":"82.3","German":"74.5","Spanish":"79.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-dutch","task":"Cross-Lingual NER","dataset":"CoNLL Dutch","model":"XLM-R large","rank_in_archive_order":7,"of":10,"metrics":{"F1":"79.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-german","task":"Cross-Lingual NER","dataset":"CoNLL German","model":"XLM-R large","rank_in_archive_order":4,"of":10,"metrics":{"F1":"74.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-conll-spanish","task":"Cross-Lingual NER","dataset":"CoNLL Spanish","model":"XLM-R large","rank_in_archive_order":1,"of":10,"metrics":{"F1":"79.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12623","atlas_url":"https://app.syntology.ai/?focus=2210.12623","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}