{"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/n-ary-relation-extraction-using-graph-state","title":"N-ary Relation Extraction using Graph State LSTM","arxiv_id":"1808.09101","date":"2018-08-28","proceeding":null,"authors":["Linfeng Song","Yue Zhang","Zhiguo Wang","Daniel Gildea"],"abstract":"Cross-sentence $n$-ary relation extraction detects relations among $n$\nentities across multiple sentences. Typical methods formulate an input as a\n\\textit{document graph}, integrating various intra-sentential and\ninter-sentential dependencies. The current state-of-the-art method splits the\ninput graph into two DAGs, adopting a DAG-structured LSTM for each. Though\nbeing able to model rich linguistic knowledge by leveraging graph edges,\nimportant information can be lost in the splitting procedure. We propose a\ngraph-state LSTM model, which uses a parallel state to model each word,\nrecurrently enriching state values via message passing. Compared with DAG\nLSTMs, our graph LSTM keeps the original graph structure, and speeds up\ncomputation by allowing more parallelization. On a standard benchmark, our\nmodel shows the best result in the literature.","url_abs":"http://arxiv.org/abs/1808.09101v1","url_pdf":"http://arxiv.org/pdf/1808.09101v1.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":"n-ary-relation-extraction-using-graph-state","repo_url":"https://github.com/freesunshine0316/nary-grn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"n-ary-relation-extraction-using-graph-state","repo_url":"https://github.com/pencoa/state-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"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":{"atlas_url":"https://app.syntology.ai/?focus=1808.09101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}