{"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/dependency-or-span-end-to-end-uniform","title":"Dependency or Span, End-to-End Uniform Semantic Role Labeling","arxiv_id":"1901.05280","date":"2019-01-16","proceeding":null,"authors":["Zuchao Li","Shexia He","Hai Zhao","Yiqing Zhang","Zhuosheng Zhang","Xi Zhou","Xiang Zhou"],"abstract":"Semantic role labeling (SRL) aims to discover the predicateargument structure\nof a sentence. End-to-end SRL without syntactic input has received great\nattention. However, most of them focus on either span-based or dependency-based\nsemantic representation form and only show specific model optimization\nrespectively. Meanwhile, handling these two SRL tasks uniformly was less\nsuccessful. This paper presents an end-to-end model for both dependency and\nspan SRL with a unified argument representation to deal with two different\ntypes of argument annotations in a uniform fashion. Furthermore, we jointly\npredict all predicates and arguments, especially including long-term ignored\npredicate identification subtask. Our single model achieves new\nstate-of-the-art results on both span (CoNLL 2005, 2012) and dependency (CoNLL\n2008, 2009) SRL benchmarks.","url_abs":"http://arxiv.org/abs/1901.05280v1","url_pdf":"http://arxiv.org/pdf/1901.05280v1.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":"dependency-or-span-end-to-end-uniform","repo_url":"https://github.com/bcmi220/unisrl","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"model-optimization","task_name":"Model Optimization"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-role-labeling-on-conll-2005","task":"Semantic Role Labeling","dataset":"CoNLL 2005","model":"Li et al. (2019) (Ensemble)","rank_in_archive_order":9,"of":15,"metrics":{"F1":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-role-labeling-on-conll-2005","task":"Semantic Role Labeling","dataset":"CoNLL 2005","model":"Li et al. (2019) + ELMo","rank_in_archive_order":11,"of":15,"metrics":{"F1":"86.3"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-role-labeling-on-conll-2005","task":"Semantic Role Labeling","dataset":"CoNLL 2005","model":"Li et al. (2019)","rank_in_archive_order":14,"of":15,"metrics":{"F1":"83.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-role-labeling-on-ontonotes","task":"Semantic Role Labeling","dataset":"OntoNotes","model":"Li et al.","rank_in_archive_order":11,"of":17,"metrics":{"F1":"86.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.05280","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}