{"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/fine-tune-bert-for-docred-with-two-step","title":"Fine-tune Bert for DocRED with Two-step Process","arxiv_id":"1909.11898","date":"2019-09-26","proceeding":null,"authors":["Hong Wang","Christfried Focke","Rob Sylvester","Nilesh Mishra","William Wang"],"abstract":"Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction. Current baselines for this task uses BiLSTM to encode the whole document and are trained from scratch. We argue that such simple baselines are not strong enough to model to complex interaction between entities. In this paper, we further apply a pre-trained language model (BERT) to provide a stronger baseline for this task. We also find that solving this task in phases can further improve the performance. The first step is to predict whether or not two entities have a relation, the second step is to predict the specific relation.","url_abs":"https://arxiv.org/abs/1909.11898v1","url_pdf":"https://arxiv.org/pdf/1909.11898v1.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":"fine-tune-bert-for-docred-with-two-step","repo_url":"https://github.com/hongwang600/DocRed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"Two-Step+BERT-base","rank_in_archive_order":55,"of":62,"metrics":{"F1":"53.92","Ign F1":"54.42"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-docred","task":"Relation Extraction","dataset":"DocRED","model":"BERT-base","rank_in_archive_order":57,"of":62,"metrics":{"F1":"53.22","Ign F1":"56.17"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1909.11898","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}