{"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-transfer-for-tagging-low-resource","title":"Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary","arxiv_id":"1705.00424","date":"2017-05-01","proceeding":"ACL 2017 7","authors":["Meng Fang","Trevor Cohn"],"abstract":"Cross-lingual model transfer is a compelling and popular method for\npredicting annotations in a low-resource language, whereby parallel corpora\nprovide a bridge to a high-resource language and its associated annotated\ncorpora. However, parallel data is not readily available for many languages,\nlimiting the applicability of these approaches. We address these drawbacks in\nour framework which takes advantage of cross-lingual word embeddings trained\nsolely on a high coverage bilingual dictionary. We propose a novel neural\nnetwork model for joint training from both sources of data based on\ncross-lingual word embeddings, and show substantial empirical improvements over\nbaseline techniques. We also propose several active learning heuristics, which\nresult in improvements over competitive benchmark methods.","url_abs":"http://arxiv.org/abs/1705.00424v1","url_pdf":"http://arxiv.org/pdf/1705.00424v1.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-transfer-for-tagging-low-resource","repo_url":"https://github.com/mengf1/trpos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"cross-lingual-word-embeddings","task_name":"Cross-Lingual Word Embeddings"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.00424","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}