{"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/sgnmt-a-flexible-nmt-decoding-platform-for","title":"SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies","arxiv_id":"1707.06885","date":"2017-07-21","proceeding":"EMNLP 2017 9","authors":["Felix Stahlberg","Eva Hasler","Danielle Saunders","Bill Byrne"],"abstract":"This paper introduces SGNMT, our experimental platform for machine\ntranslation research. SGNMT provides a generic interface to neural and symbolic\nscoring modules (predictors) with left-to-right semantic such as translation\nmodels like NMT, language models, translation lattices, $n$-best lists or other\nkinds of scores and constraints. Predictors can be combined with other\npredictors to form complex decoding tasks. SGNMT implements a number of search\nstrategies for traversing the space spanned by the predictors which are\nappropriate for different predictor constellations. Adding new predictors or\ndecoding strategies is particularly easy, making it a very efficient tool for\nprototyping new research ideas. SGNMT is actively being used by students in the\nMPhil program in Machine Learning, Speech and Language Technology at the\nUniversity of Cambridge for course work and theses, as well as for most of the\nresearch work in our group.","url_abs":"http://arxiv.org/abs/1707.06885v1","url_pdf":"http://arxiv.org/pdf/1707.06885v1.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":"sgnmt-a-flexible-nmt-decoding-platform-for","repo_url":"https://github.com/ucam-smt/sgnmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06885","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}