{"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/lessons-learned-in-multilingual-grounded","title":"Lessons learned in multilingual grounded language learning","arxiv_id":"1809.07615","date":"2018-09-20","proceeding":"CONLL 2018 10","authors":["Ákos Kádár","Desmond Elliott","Marc-Alexandre Côté","Grzegorz Chrupała","Afra Alishahi"],"abstract":"Recent work has shown how to learn better visual-semantic embeddings by\nleveraging image descriptions in more than one language. Here, we investigate\nin detail which conditions affect the performance of this type of grounded\nlanguage learning model. We show that multilingual training improves over\nbilingual training, and that low-resource languages benefit from training with\nhigher-resource languages. We demonstrate that a multilingual model can be\ntrained equally well on either translations or comparable sentence pairs, and\nthat annotating the same set of images in multiple language enables further\nimprovements via an additional caption-caption ranking objective.","url_abs":"http://arxiv.org/abs/1809.07615v1","url_pdf":"http://arxiv.org/pdf/1809.07615v1.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":"lessons-learned-in-multilingual-grounded","repo_url":"https://github.com/kadarakos/mulisera","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"grounded-language-learning","task_name":"Grounded language learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.07615","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}