{"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/graphie-a-graph-based-framework-for","title":"GraphIE: A Graph-Based Framework for Information Extraction","arxiv_id":"1810.13083","date":"2018-10-31","proceeding":"NAACL 2019 6","authors":["Yujie Qian","Enrico Santus","Zhijing Jin","Jiang Guo","Regina Barzilay"],"abstract":"Most modern Information Extraction (IE) systems are implemented as sequential\ntaggers and only model local dependencies. Non-local and non-sequential context\nis, however, a valuable source of information to improve predictions. In this\npaper, we introduce GraphIE, a framework that operates over a graph\nrepresenting a broad set of dependencies between textual units (i.e. words or\nsentences). The algorithm propagates information between connected nodes\nthrough graph convolutions, generating a richer representation that can be\nexploited to improve word-level predictions. Evaluation on three different\ntasks --- namely textual, social media and visual information extraction ---\nshows that GraphIE consistently outperforms the state-of-the-art sequence\ntagging model by a significant margin.","url_abs":"http://arxiv.org/abs/1810.13083v3","url_pdf":"http://arxiv.org/pdf/1810.13083v3.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":"graphie-a-graph-based-framework-for","repo_url":"https://github.com/thomas0809/GraphIE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graphie-a-graph-based-framework-for","repo_url":"https://github.com/polynoman/The-Annotated-GraphIE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.13083","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}