{"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/extracting-or-guessing-improving-faithfulness","title":"Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction","arxiv_id":"2210.04992","date":"2022-10-10","proceeding":null,"authors":["Haoyu Wang","Hongming Zhang","Yuqian Deng","Jacob R. Gardner","Dan Roth","Muhao Chen"],"abstract":"In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description. To achieve this, we propose to conduct counterfactual analysis to attenuate the effects of two significant types of training biases: the event trigger bias and the frequent label bias. We also add tense information into event representations to explicitly place an emphasis on the contextual description. The second perspective is to provide proper uncertainty estimation and abstain from extraction when no relation is described in the text. By parameterization of Dirichlet Prior over the model-predicted categorical distribution, we improve the model estimates of the correctness likelihood and make TempRel predictions more selective. We also employ temperature scaling to recalibrate the model confidence measure after bias mitigation. Through experimental analysis on MATRES, MATRES-DS, and TDDiscourse, we demonstrate that our model extracts TempRel and timelines more faithfully compared to SOTA methods, especially under distribution shifts.","url_abs":"https://arxiv.org/abs/2210.04992v2","url_pdf":"https://arxiv.org/pdf/2210.04992v2.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":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"temporal-relation-classification","task_name":"Temporal Relation Classification"},{"task_slug":"temporal-relation-extraction","task_name":"Temporal Relation Extraction"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-relation-classification-on-matres","task":"Temporal Relation Classification","dataset":"MATRES","model":"Faithfulness","rank_in_archive_order":3,"of":4,"metrics":{"F1":"82.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2210.04992","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}