{"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/deep-semantic-role-labeling-what-works-and","title":"Deep Semantic Role Labeling: What Works and What's Next","arxiv_id":null,"date":"2017-07-01","proceeding":"ACL 2017 7","authors":["Luheng He","Kenton Lee","Mike Lewis","Luke Zettlemoyer"],"abstract":"We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway BiLSTM architecture with constrained decoding, while observing a number of recent best practices for initialization and regularization. Our 8-layer ensemble model achieves 83.2 F1 on theCoNLL 2005 test set and 83.4 F1 on CoNLL 2012, roughly a 10{\\%} relative error reduction over the previous state of the art. Extensive empirical analysis of these gains show that (1) deep models excel at recovering long-distance dependencies but can still make surprisingly obvious errors, and (2) that there is still room for syntactic parsers to improve these results.","url_abs":"https://aclanthology.org/P17-1044","url_pdf":"https://aclanthology.org/P17-1044.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":"deep-semantic-role-labeling-what-works-and","repo_url":"https://github.com/luheng/deep_srl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"predicate-detection","task_name":"Predicate Detection"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/predicate-detection-on-conll-2005","task":"Predicate Detection","dataset":"CoNLL 2005","model":"DeepSRL","rank_in_archive_order":2,"of":2,"metrics":{"F1":"96.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-role-labeling-on-ontonotes","task":"Semantic Role Labeling","dataset":"OntoNotes","model":"He et al.","rank_in_archive_order":17,"of":17,"metrics":{"F1":"81.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}