{"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/reviewing-labels-label-graph-network-with-top","title":"Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction","arxiv_id":"2212.14270","date":"2022-12-29","proceeding":null,"authors":["Bo Li","Wei Ye","Jinglei Zhang","Shikun Zhang"],"abstract":"The typical way for relation extraction is fine-tuning large pre-trained language models on task-specific datasets, then selecting the label with the highest probability of the output distribution as the final prediction. However, the usage of the Top-k prediction set for a given sample is commonly overlooked. In this paper, we first reveal that the Top-k prediction set of a given sample contains useful information for predicting the correct label. To effectively utilizes the Top-k prediction set, we propose Label Graph Network with Top-k Prediction Set, termed as KLG. Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them. We also design a dynamic $k$-selection mechanism to learn more powerful and discriminative relation representation. Our experiments show that KLG achieves the best performances on three relation extraction datasets. Moreover, we observe that KLG is more effective in dealing with long-tailed classes.","url_abs":"https://arxiv.org/abs/2212.14270v1","url_pdf":"https://arxiv.org/pdf/2212.14270v1.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":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-semeval-2010-task-8","task":"Relation Extraction","dataset":"SemEval-2010 Task-8","model":"KLG","rank_in_archive_order":5,"of":31,"metrics":{"F1":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-tacred-revisited","task":"Relation Extraction","dataset":"TACRED-Revisited","model":"KLG","rank_in_archive_order":2,"of":3,"metrics":{"F1":"84.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.14270","atlas_url":"https://app.syntology.ai/?focus=2212.14270","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}