{"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/lium-machine-translation-systems-for-wmt17","title":"LIUM Machine Translation Systems for WMT17 News Translation Task","arxiv_id":"1707.04499","date":"2017-07-14","proceeding":"WS 2017 9","authors":["Mercedes García-Martínez","Ozan Caglayan","Walid Aransa","Adrien Bardet","Fethi Bougares","Loïc Barrault"],"abstract":"This paper describes LIUM submissions to WMT17 News Translation Task for\nEnglish-German, English-Turkish, English-Czech and English-Latvian language\npairs. We train BPE-based attentive Neural Machine Translation systems with and\nwithout factored outputs using the open source nmtpy framework. Competitive\nscores were obtained by ensembling various systems and exploiting the\navailability of target monolingual corpora for back-translation. The impact of\nback-translation quantity and quality is also analyzed for English-Turkish\nwhere our post-deadline submission surpassed the best entry by +1.6 BLEU.","url_abs":"http://arxiv.org/abs/1707.04499v1","url_pdf":"http://arxiv.org/pdf/1707.04499v1.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":"lium-machine-translation-systems-for-wmt17","repo_url":"https://github.com/lium-lst/wmt17-newstask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.04499","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}