{"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/a-simple-and-effective-method-to-eliminate","title":"A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations","arxiv_id":"2109.04727","date":"2021-09-10","proceeding":"EMNLP 2021 11","authors":["ZiYi Yang","Yinfei Yang","Daniel Cer","Eric Darve"],"abstract":"Language agnostic and semantic-language information isolation is an emerging research direction for multilingual representations models. We explore this problem from a novel angle of geometric algebra and semantic space. A simple but highly effective method \"Language Information Removal (LIR)\" factors out language identity information from semantic related components in multilingual representations pre-trained on multi-monolingual data. A post-training and model-agnostic method, LIR only uses simple linear operations, e.g. matrix factorization and orthogonal projection. LIR reveals that for weak-alignment multilingual systems, the principal components of semantic spaces primarily encodes language identity information. We first evaluate the LIR on a cross-lingual question answer retrieval task (LAReQA), which requires the strong alignment for the multilingual embedding space. Experiment shows that LIR is highly effectively on this task, yielding almost 100% relative improvement in MAP for weak-alignment models. We then evaluate the LIR on Amazon Reviews and XEVAL dataset, with the observation that removing language information is able to improve the cross-lingual transfer performance.","url_abs":"https://arxiv.org/abs/2109.04727v1","url_pdf":"https://arxiv.org/pdf/2109.04727v1.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":"a-simple-and-effective-method-to-eliminate","repo_url":"https://github.com/ziyi-yang/lir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.04727","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}