{"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/contextual-encoding-for-translation-quality","title":"Contextual Encoding for Translation Quality Estimation","arxiv_id":"1809.00129","date":"2018-09-01","proceeding":"WS 2018 10","authors":["Junjie Hu","Wei-Cheng Chang","Yuexin Wu","Graham Neubig"],"abstract":"The task of word-level quality estimation (QE) consists of taking a source\nsentence and machine-generated translation, and predicting which words in the\noutput are correct and which are wrong.\n  In this paper, propose a method to effectively encode the local and global\ncontextual information for each target word using a three-part neural network\napproach.\n  The first part uses an embedding layer to represent words and their\npart-of-speech tags in both languages. The second part leverages a\none-dimensional convolution layer to integrate local context information for\neach target word. The third part applies a stack of feed-forward and recurrent\nneural networks to further encode the global context in the sentence before\nmaking the predictions. This model was submitted as the CMU entry to the\nWMT2018 shared task on QE, and achieves strong results, ranking first in three\nof the six tracks.","url_abs":"http://arxiv.org/abs/1809.00129v1","url_pdf":"http://arxiv.org/pdf/1809.00129v1.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":"contextual-encoding-for-translation-quality","repo_url":"https://github.com/junjiehu/CEQE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}