{"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/adapting-sequence-models-for-sentence","title":"Adapting Sequence Models for Sentence Correction","arxiv_id":"1707.09067","date":"2017-07-27","proceeding":"EMNLP 2017 9","authors":["Allen Schmaltz","Yoon Kim","Alexander M. Rush","Stuart M. Shieber"],"abstract":"In a controlled experiment of sequence-to-sequence approaches for the task of\nsentence correction, we find that character-based models are generally more\neffective than word-based models and models that encode subword information via\nconvolutions, and that modeling the output data as a series of diffs improves\neffectiveness over standard approaches. Our strongest sequence-to-sequence\nmodel improves over our strongest phrase-based statistical machine translation\nmodel, with access to the same data, by 6 M2 (0.5 GLEU) points. Additionally,\nin the data environment of the standard CoNLL-2014 setup, we demonstrate that\nmodeling (and tuning against) diffs yields similar or better M2 scores with\nsimpler models and/or significantly less data than previous\nsequence-to-sequence approaches.","url_abs":"http://arxiv.org/abs/1707.09067v1","url_pdf":"http://arxiv.org/pdf/1707.09067v1.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":"adapting-sequence-models-for-sentence","repo_url":"https://github.com/allenschmaltz/grammar","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":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.09067","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}