{"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/machine-created-universal-language-for-cross","title":"Machine-Created Universal Language for Cross-lingual Transfer","arxiv_id":"2305.13071","date":"2023-05-22","proceeding":null,"authors":["Yaobo Liang","Quanzhi Zhu","Junhe Zhao","Nan Duan"],"abstract":"There are two primary approaches to addressing cross-lingual transfer: multilingual pre-training, which implicitly aligns the hidden representations of various languages, and translate-test, which explicitly translates different languages into an intermediate language, such as English. Translate-test offers better interpretability compared to multilingual pre-training. However, it has lower performance than multilingual pre-training(Conneau and Lample, 2019; Conneau et al, 2020) and struggles with word-level tasks due to translation altering word order. As a result, we propose a new Machine-created Universal Language (MUL) as an alternative intermediate language. MUL comprises a set of discrete symbols forming a universal vocabulary and a natural language to MUL translator for converting multiple natural languages to MUL. MUL unifies shared concepts from various languages into a single universal word, enhancing cross-language transfer. Additionally, MUL retains language-specific words and word order, allowing the model to be easily applied to word-level tasks. Our experiments demonstrate that translating into MUL yields improved performance compared to multilingual pre-training, and our analysis indicates that MUL possesses strong interpretability. The code is at: https://github.com/microsoft/Unicoder/tree/master/MCUL.","url_abs":"https://arxiv.org/abs/2305.13071v2","url_pdf":"https://arxiv.org/pdf/2305.13071v2.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":"machine-created-universal-language-for-cross","repo_url":"https://github.com/microsoft/Unicoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.13071","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}