{"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/unsupervised-multilingual-word-embeddings","title":"Unsupervised Multilingual Word Embeddings","arxiv_id":"1808.08933","date":"2018-08-27","proceeding":"EMNLP 2018 10","authors":["Xilun Chen","Claire Cardie"],"abstract":"Multilingual Word Embeddings (MWEs) represent words from multiple languages\nin a single distributional vector space. Unsupervised MWE (UMWE) methods\nacquire multilingual embeddings without cross-lingual supervision, which is a\nsignificant advantage over traditional supervised approaches and opens many new\npossibilities for low-resource languages. Prior art for learning UMWEs,\nhowever, merely relies on a number of independently trained Unsupervised\nBilingual Word Embeddings (UBWEs) to obtain multilingual embeddings. These\nmethods fail to leverage the interdependencies that exist among many languages.\nTo address this shortcoming, we propose a fully unsupervised framework for\nlearning MWEs that directly exploits the relations between all language pairs.\nOur model substantially outperforms previous approaches in the experiments on\nmultilingual word translation and cross-lingual word similarity. In addition,\nour model even beats supervised approaches trained with cross-lingual\nresources.","url_abs":"http://arxiv.org/abs/1808.08933v2","url_pdf":"http://arxiv.org/pdf/1808.08933v2.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":"unsupervised-multilingual-word-embeddings","repo_url":"https://github.com/ccsasuke/umwe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unsupervised-multilingual-word-embeddings","repo_url":"https://github.com/selimseker/logogram-language-generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unsupervised-multilingual-word-embeddings","repo_url":"https://github.com/soumyaumass/umwe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multilingual-word-embeddings","task_name":"Multilingual Word Embeddings"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-similarity","task_name":"Word Similarity"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08933","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}