{"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-robust-self-learning-method-for-fully","title":"A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings","arxiv_id":"1805.06297","date":"2018-05-16","proceeding":"ACL 2018 7","authors":["Mikel Artetxe","Gorka Labaka","Eneko Agirre"],"abstract":"Recent work has managed to learn cross-lingual word embeddings without\nparallel data by mapping monolingual embeddings to a shared space through\nadversarial training. However, their evaluation has focused on favorable\nconditions, using comparable corpora or closely-related languages, and we show\nthat they often fail in more realistic scenarios. This work proposes an\nalternative approach based on a fully unsupervised initialization that\nexplicitly exploits the structural similarity of the embeddings, and a robust\nself-learning algorithm that iteratively improves this solution. Our method\nsucceeds in all tested scenarios and obtains the best published results in\nstandard datasets, even surpassing previous supervised systems. Our\nimplementation is released as an open source project at\nhttps://github.com/artetxem/vecmap","url_abs":"http://arxiv.org/abs/1805.06297v2","url_pdf":"http://arxiv.org/pdf/1805.06297v2.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-robust-self-learning-method-for-fully","repo_url":"https://github.com/artetxem/vecmap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-robust-self-learning-method-for-fully","repo_url":"https://github.com/earthspecies/audio-embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-word-embeddings","task_name":"Cross-Lingual Word Embeddings"},{"task_slug":"self-learning","task_name":"Self-Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06297","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}