{"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/ensembling-factored-neural-machine","title":"Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation","arxiv_id":"1706.05083","date":"2017-06-15","proceeding":"WS 2017 9","authors":["Chris Hokamp"],"abstract":"This work presents a novel approach to Automatic Post-Editing (APE) and\nWord-Level Quality Estimation (QE) using ensembles of specialized Neural\nMachine Translation (NMT) systems. Word-level features that have proven\neffective for QE are included as input factors, expanding the representation of\nthe original source and the machine translation hypothesis, which are used to\ngenerate an automatically post-edited hypothesis. We train a suite of NMT\nmodels that use different input representations, but share the same output\nspace. These models are then ensembled together, and tuned for both the APE and\nthe QE task. We thus attempt to connect the state-of-the-art approaches to APE\nand QE within a single framework. Our models achieve state-of-the-art results\nin both tasks, with the only difference in the tuning step which learns weights\nfor each component of the ensemble.","url_abs":"http://arxiv.org/abs/1706.05083v2","url_pdf":"http://arxiv.org/pdf/1706.05083v2.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":"ensembling-factored-neural-machine","repo_url":"https://github.com/chrishokamp/constrained_decoding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"automatic-post-editing","task_name":"Automatic Post-Editing"},{"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":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1706.05083","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}