{"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/tuplemax-loss-for-language-identification","title":"Tuplemax Loss for Language Identification","arxiv_id":"1811.12290","date":"2018-11-29","proceeding":null,"authors":["Li Wan","Prashant Sridhar","Yang Yu","Quan Wang","Ignacio Lopez Moreno"],"abstract":"In many scenarios of a language identification task, the user will specify a\nsmall set of languages which he/she can speak instead of a large set of all\npossible languages. We want to model such prior knowledge into the way we train\nour neural networks, by replacing the commonly used softmax loss function with\na novel loss function named tuplemax loss. As a matter of fact, a typical\nlanguage identification system launched in North America has about 95% users\nwho could speak no more than two languages. Using the tuplemax loss, our system\nachieved a 2.33% error rate, which is a relative 39.4% improvement over the\n3.85% error rate of standard softmax loss method.","url_abs":"http://arxiv.org/abs/1811.12290v2","url_pdf":"http://arxiv.org/pdf/1811.12290v2.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":"tuplemax-loss-for-language-identification","repo_url":"https://github.com/widdiot/Tuplemax-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-identification","task_name":"Language Identification"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}