{"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/a-full-end-to-end-semantic-role-labeler-1","title":"A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?","arxiv_id":"1808.03815","date":"2018-08-11","proceeding":null,"authors":["Jiaxun Cai","Shexia He","Zuchao Li","Hai Zhao"],"abstract":"Semantic role labeling (SRL) is to recognize the predicate-argument structure\nof a sentence, including subtasks of predicate disambiguation and argument\nlabeling. Previous studies usually formulate the entire SRL problem into two or\nmore subtasks. For the first time, this paper introduces an end-to-end neural\nmodel which unifiedly tackles the predicate disambiguation and the argument\nlabeling in one shot. Using a biaffine scorer, our model directly predicts all\nsemantic role labels for all given word pairs in the sentence without relying\non any syntactic parse information. Specifically, we augment the BiLSTM encoder\nwith a non-linear transformation to further distinguish the predicate and the\nargument in a given sentence, and model the semantic role labeling process as a\nword pair classification task by employing the biaffine attentional mechanism.\nThough the proposed model is syntax-agnostic with local decoder, it outperforms\nthe state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009\nbenchmarks for both English and Chinese. To our best knowledge, we report the\nfirst syntax-agnostic SRL model that surpasses all known syntax-aware models.","url_abs":"http://arxiv.org/abs/1808.03815v2","url_pdf":"http://arxiv.org/pdf/1808.03815v2.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":"a-full-end-to-end-semantic-role-labeler-1","repo_url":"https://github.com/JiaxunCai/Dynet-Biaffine-SRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"sentence","task_name":"Sentence"}],"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.03815","atlas_url":"https://app.syntology.ai/?focus=1808.03815","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}