{"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/auxiliary-objectives-for-neural-error","title":"Auxiliary Objectives for Neural Error Detection Models","arxiv_id":"1707.05227","date":"2017-07-17","proceeding":"WS 2017 9","authors":["Marek Rei","Helen Yannakoudakis"],"abstract":"We investigate the utility of different auxiliary objectives and training\nstrategies within a neural sequence labeling approach to error detection in\nlearner writing. Auxiliary costs provide the model with additional linguistic\ninformation, allowing it to learn general-purpose compositional features that\ncan then be exploited for other objectives. Our experiments show that a joint\nlearning approach trained with parallel labels on in-domain data improves\nperformance over the previous best error detection system. While the resulting\nmodel has the same number of parameters, the additional objectives allow it to\nbe optimised more efficiently and achieve better performance.","url_abs":"http://arxiv.org/abs/1707.05227v1","url_pdf":"http://arxiv.org/pdf/1707.05227v1.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":[],"tasks":[{"task_slug":"grammatical-error-detection","task_name":"Grammatical Error Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a1","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A1","model":"Bi-LSTM + POS (unrestricted data)","rank_in_archive_order":2,"of":8,"metrics":{"F0.5":"36.1"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a1","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A1","model":"Bi-LSTM + POS (trained on FCE)","rank_in_archive_order":7,"of":8,"metrics":{"F0.5":"17.5"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a2","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A2","model":"Bi-LSTM + POS (unrestricted data)","rank_in_archive_order":2,"of":8,"metrics":{"F0.5":"45.1"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-conll-2014-a2","task":"Grammatical Error Detection","dataset":"CoNLL-2014 A2","model":"Bi-LSTM + POS (trained on FCE)","rank_in_archive_order":6,"of":8,"metrics":{"F0.5":"26.2"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-detection-on-fce","task":"Grammatical Error Detection","dataset":"FCE","model":"Bi-LSTM + err POS GR","rank_in_archive_order":5,"of":8,"metrics":{"F0.5":"47.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.05227","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}