{"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/neural-relation-extraction-within-and-across","title":"Neural Relation Extraction Within and Across Sentence Boundaries","arxiv_id":"1810.05102","date":"2018-10-11","proceeding":null,"authors":["Pankaj Gupta","Subburam Rajaram","Hinrich Schütze","Bernt Andrassy","Thomas Runkler"],"abstract":"Past work in relation extraction mostly focuses on binary relation between\nentity pairs within single sentence. Recently, the NLP community has gained\ninterest in relation extraction in entity pairs spanning multiple sentences. In\nthis paper, we propose a novel architecture for this task: inter-sentential\ndependency-based neural networks (iDepNN). iDepNN models the shortest and\naugmented dependency paths via recurrent and recursive neural networks to\nextract relationships within (intra-) and across (inter-) sentence boundaries.\nCompared to SVM and neural network baselines, iDepNN is more robust to false\npositives in relationships spanning sentences.\n  We evaluate our models on four datasets from newswire (MUC6) and medical\n(BioNLP shared task) domains that achieve state-of-the-art performance and show\na better balance in precision and recall for inter-sentential relationships. We\nperform better than 11 teams participating in the BioNLP shared task 2016 and\nachieve a gain of 5.2% (0.587 vs 0.558) in F1 over the winning team. We also\nrelease the crosssentence annotations for MUC6.","url_abs":"http://arxiv.org/abs/1810.05102v2","url_pdf":"http://arxiv.org/pdf/1810.05102v2.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":"neural-relation-extraction-within-and-across","repo_url":"https://github.com/pgcool/Cross-sentence-Relation-Extraction-iDepNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","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":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-muc6","task":"Relation Extraction","dataset":"MUC6","model":"iDepNN","rank_in_archive_order":1,"of":1,"metrics":{"Average F1":".940"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.05102","atlas_url":"https://app.syntology.ai/?focus=1810.05102","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}