{"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/the-limitations-of-cross-language-word","title":"The Limitations of Cross-language Word Embeddings Evaluation","arxiv_id":"1806.02253","date":"2018-06-06","proceeding":"SEMEVAL 2018 6","authors":["Amir Bakarov","Roman Suvorov","Ilya Sochenkov"],"abstract":"The aim of this work is to explore the possible limitations of existing\nmethods of cross-language word embeddings evaluation, addressing the lack of\ncorrelation between intrinsic and extrinsic cross-language evaluation methods.\nTo prove this hypothesis, we construct English-Russian datasets for extrinsic\nand intrinsic evaluation tasks and compare performances of 5 different\ncross-language models on them. The results say that the scores even on\ndifferent intrinsic benchmarks do not correlate to each other. We can conclude\nthat the use of human references as ground truth for cross-language word\nembeddings is not proper unless one does not understand how do native speakers\nprocess semantics in their cognition.","url_abs":"http://arxiv.org/abs/1806.02253v1","url_pdf":"http://arxiv.org/pdf/1806.02253v1.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":"the-limitations-of-cross-language-word","repo_url":"https://github.com/bakarov/cross-lang-embeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"embeddings-evaluation","task_name":"Embeddings Evaluation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}