{"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/vaediff-docre-end-to-end-data-augmentation","title":"VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction","arxiv_id":"2412.13503","date":"2024-12-18","proceeding":null,"authors":["Khai Phan Tran","Wen Hua","Xue Li"],"abstract":"Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets. To tackle this challenge, we propose a novel data augmentation approach using generative models to enhance data from the embedding space. Our method leverages the Variational Autoencoder (VAE) architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. To better capture the multi-label nature of DocRE, we parameterize the VAE's latent space with a Diffusion Model. Additionally, we introduce a hierarchical training framework to integrate the proposed VAE-based augmentation module into DocRE systems. Experiments on two benchmark datasets demonstrate that our method outperforms state-of-the-art models, effectively addressing the long-tail distribution problem in DocRE.","url_abs":"https://arxiv.org/abs/2412.13503v2","url_pdf":"https://arxiv.org/pdf/2412.13503v2.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":"vaediff-docre-end-to-end-data-augmentation","repo_url":"https://github.com/khaitran22/vaediff-docre","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-level-relation-extraction-on-dwie","task":"Document-level Relation Extraction","dataset":"DWIE","model":"VaeDiff-DocRE","rank_in_archive_order":1,"of":1,"metrics":{"F1":"0.7307"},"uses_additional_data":false},{"leaderboard":"/sota/document-level-relation-extraction-on-re","task":"Document-level Relation Extraction","dataset":"Re-DocRED","model":"VaeDiff-DocRE","rank_in_archive_order":1,"of":1,"metrics":{"F1":"0.7903"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}