{"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/contrastive-triple-extraction-with-generative","title":"Contrastive Triple Extraction with Generative Transformer","arxiv_id":"2009.06207","date":"2020-09-14","proceeding":null,"authors":["Hongbin Ye","Ningyu Zhang","Shumin Deng","Mosha Chen","Chuanqi Tan","Fei Huang","Huajun Chen"],"abstract":"Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative triple extraction may struggle to capture long-term dependencies and generate unfaithful triples, we introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object. Moreover, we introduce two mechanisms to further improve model performance (i.e., batch-wise dynamic attention-masking and triple-wise calibration). Experimental results on three datasets (i.e., NYT, WebNLG, and MIE) show that our approach achieves better performance than that of baselines.","url_abs":"https://arxiv.org/abs/2009.06207v8","url_pdf":"https://arxiv.org/pdf/2009.06207v8.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":[],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-webnlg","task":"Relation Extraction","dataset":"WebNLG","model":"CGT(UniLM)","rank_in_archive_order":9,"of":14,"metrics":{"F1":"83.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.06207","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}