{"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/jointly-extracting-relations-with-class-ties","title":"Jointly Extracting Relations with Class Ties via Effective Deep Ranking","arxiv_id":"1612.07602","date":"2016-12-22","proceeding":"ACL 2017 7","authors":["Hai Ye","WenHan Chao","Zhunchen Luo","Zhoujun Li"],"abstract":"Connections between relations in relation extraction, which we call class\nties, are common. In distantly supervised scenario, one entity tuple may have\nmultiple relation facts. Exploiting class ties between relations of one entity\ntuple will be promising for distantly supervised relation extraction. However,\nprevious models are not effective or ignore to model this property. In this\nwork, to effectively leverage class ties, we propose to make joint relation\nextraction with a unified model that integrates convolutional neural network\n(CNN) with a general pairwise ranking framework, in which three novel ranking\nloss functions are introduced. Additionally, an effective method is presented\nto relieve the severe class imbalance problem from NR (not relation) for model\ntraining. Experiments on a widely used dataset show that leveraging class ties\nwill enhance extraction and demonstrate the effectiveness of our model to learn\nclass ties. Our model outperforms the baselines significantly, achieving\nstate-of-the-art performance.","url_abs":"http://arxiv.org/abs/1612.07602v4","url_pdf":"http://arxiv.org/pdf/1612.07602v4.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":"jointly-extracting-relations-with-class-ties","repo_url":"https://github.com/oceanypt/DR_RE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}