{"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/isovec-controlling-the-relative-isomorphism","title":"IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces","arxiv_id":"2210.05098","date":"2022-10-11","proceeding":null,"authors":["Kelly Marchisio","Neha Verma","Kevin Duh","Philipp Koehn"],"abstract":"The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of \"isomorphism.\" We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the Skip-gram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec.","url_abs":"https://arxiv.org/abs/2210.05098v3","url_pdf":"https://arxiv.org/pdf/2210.05098v3.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":"isovec-controlling-the-relative-isomorphism","repo_url":"https://github.com/kellymarchisio/isovec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bilingual-lexicon-induction","task_name":"Bilingual Lexicon Induction"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.05098","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}