{"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/multimodal-machine-translation-with-embedding","title":"Multimodal Machine Translation with Embedding Prediction","arxiv_id":"1904.00639","date":"2019-04-01","proceeding":"NAACL 2019 6","authors":["Tosho Hirasawa","Hayahide Yamagishi","Yukio Matsumura","Mamoru Komachi"],"abstract":"Multimodal machine translation is an attractive application of neural machine\ntranslation (NMT). It helps computers to deeply understand visual objects and\ntheir relations with natural languages. However, multimodal NMT systems suffer\nfrom a shortage of available training data, resulting in poor performance for\ntranslating rare words. In NMT, pretrained word embeddings have been shown to\nimprove NMT of low-resource domains, and a search-based approach is proposed to\naddress the rare word problem. In this study, we effectively combine these two\napproaches in the context of multimodal NMT and explore how we can take full\nadvantage of pretrained word embeddings to better translate rare words. We\nreport overall performance improvements of 1.24 METEOR and 2.49 BLEU and\nachieve an improvement of 7.67 F-score for rare word translation.","url_abs":"http://arxiv.org/abs/1904.00639v1","url_pdf":"http://arxiv.org/pdf/1904.00639v1.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":"multimodal-machine-translation-with-embedding","repo_url":"https://github.com/toshohirasawa/nmtpytorch-emb-pred","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multimodal-machine-translation","task_name":"Multimodal Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-translation","task_name":"Word Translation"}],"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}