{"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/end-to-end-relation-extraction-using-lstms-on","title":"End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures","arxiv_id":"1601.00770","date":"2016-01-05","proceeding":"ACL 2016 8","authors":["Makoto Miwa","Mohit Bansal"],"abstract":"We present a novel end-to-end neural model to extract entities and relations\nbetween them. Our recurrent neural network based model captures both word\nsequence and dependency tree substructure information by stacking bidirectional\ntree-structured LSTM-RNNs on bidirectional sequential LSTM-RNNs. This allows\nour model to jointly represent both entities and relations with shared\nparameters in a single model. We further encourage detection of entities during\ntraining and use of entity information in relation extraction via entity\npretraining and scheduled sampling. Our model improves over the\nstate-of-the-art feature-based model on end-to-end relation extraction,\nachieving 12.1% and 5.7% relative error reductions in F1-score on ACE2005 and\nACE2004, respectively. We also show that our LSTM-RNN based model compares\nfavorably to the state-of-the-art CNN based model (in F1-score) on nominal\nrelation classification (SemEval-2010 Task 8). Finally, we present an extensive\nablation analysis of several model components.","url_abs":"http://arxiv.org/abs/1601.00770v3","url_pdf":"http://arxiv.org/pdf/1601.00770v3.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":"end-to-end-relation-extraction-using-lstms-on","repo_url":"https://github.com/Meet1995/Named-Entity-Recognition-And-Relationship-Linking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"end-to-end-relation-extraction-using-lstms-on","repo_url":"https://github.com/tticoin/LSTM-ER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-ace-2004","task":"Relation Extraction","dataset":"ACE 2004","model":"SPTree","rank_in_archive_order":6,"of":11,"metrics":{"Cross Sentence":"No","NER Micro F1":"81.8","RE+ Micro F1":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ace-2005","task":"Relation Extraction","dataset":"ACE 2005","model":"SPTree","rank_in_archive_order":21,"of":30,"metrics":{"Cross Sentence":"No","NER Micro F1":"83.4","RE+ Micro F1":"55.6","Sentence Encoder":"biLSTM"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-nyt11-hrl","task":"Relation Extraction","dataset":"NYT11-HRL","model":"SPTree","rank_in_archive_order":8,"of":12,"metrics":{"F1":"53.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1601.00770","atlas_url":"https://app.syntology.ai/?focus=1601.00770","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}