{"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/multilingual-models-for-compositional","title":"Multilingual Models for Compositional Distributed Semantics","arxiv_id":"1404.4641","date":"2014-04-17","proceeding":"ACL 2014 6","authors":["Karl Moritz Hermann","Phil Blunsom"],"abstract":"We present a novel technique for learning semantic representations, which\nextends the distributional hypothesis to multilingual data and joint-space\nembeddings. Our models leverage parallel data and learn to strongly align the\nembeddings of semantically equivalent sentences, while maintaining sufficient\ndistance between those of dissimilar sentences. The models do not rely on word\nalignments or any syntactic information and are successfully applied to a\nnumber of diverse languages. We extend our approach to learn semantic\nrepresentations at the document level, too. We evaluate these models on two\ncross-lingual document classification tasks, outperforming the prior state of\nthe art. Through qualitative analysis and the study of pivoting effects we\ndemonstrate that our representations are semantically plausible and can capture\nsemantic relationships across languages without parallel data.","url_abs":"http://arxiv.org/abs/1404.4641v1","url_pdf":"http://arxiv.org/pdf/1404.4641v1.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":"multilingual-models-for-compositional","repo_url":"https://github.com/karlmoritz/bicvm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"cross-lingual-document-classification","task_name":"Cross-Lingual Document Classification"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"learning-semantic-representations","task_name":"Learning Semantic Representations"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-document-classification-on-12","task":"Cross-Lingual Document Classification","dataset":"Reuters RCV1/RCV2 English-to-German","model":"Bi+","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"88.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-document-classification-on-13","task":"Cross-Lingual Document Classification","dataset":"Reuters RCV1/RCV2 German-to-English","model":"Bi+","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"79.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1404.4641","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}