{"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/rebel-relation-extraction-by-end-to-end","title":"REBEL: Relation Extraction By End-to-end Language generation","arxiv_id":null,"date":"2021-10-29","proceeding":"Findings (EMNLP) 2021 11","authors":["Pere-Lluis Huguet Cabot","Roberto Navigli"],"abstract":"Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-step pipelines that propagate errors or are limited to a small number of relation types. To overcome these issues, we propose the use of autoregressive seq2seq models. Such models have previously been shown to perform well not only in language generation, but also in NLU tasks such as Entity Linking, thanks to their framing as seq2seq tasks.\r\nIn this paper, we show how Relation Extraction can be simplified by expressing triplets as a sequence of text and we present REBEL, a seq2seq model based on BART that performs end-to-end relation extraction for more than 200 different relation types. We show our model's flexibility by fine-tuning it on an array of Relation Extraction and Relation Classification benchmarks, with it attaining state-of-the-art performance in most of them.","url_abs":"https://github.com/Babelscape/rebel","url_pdf":"https://github.com/Babelscape/rebel/blob/main/docs/EMNLP_2021_REBEL__Camera_Ready_.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":"rebel-relation-extraction-by-end-to-end","repo_url":"https://github.com/Babelscape/rebel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"rebel-dataset","name":"REBEL","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-3","task":"Joint Entity and Relation Extraction","dataset":"DocRED","model":"REBEL+pretraining","rank_in_archive_order":1,"of":6,"metrics":{"Relation F1":"47.1"},"uses_additional_data":true},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-3","task":"Joint Entity and Relation Extraction","dataset":"DocRED","model":"REBEL","rank_in_archive_order":2,"of":6,"metrics":{"Relation F1":"41.8"},"uses_additional_data":true},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"REBEL (including overlapping entities)","rank_in_archive_order":6,"of":15,"metrics":{"RE+ Macro F1":"82.2"},"uses_additional_data":true},{"leaderboard":"/sota/relation-extraction-on-conll04","task":"Relation Extraction","dataset":"CoNLL04","model":"REBEL","rank_in_archive_order":1,"of":16,"metrics":{"RE+ Macro F1 ":"76.65","RE+ Micro F1":"75.4"},"uses_additional_data":true},{"leaderboard":"/sota/relation-extraction-on-nyt","task":"Relation Extraction","dataset":"NYT","model":"REBEL (no pre-training)","rank_in_archive_order":5,"of":8,"metrics":{"F1":"93.1"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-re-tacred","task":"Relation Extraction","dataset":"Re-TACRED","model":"REBEL (no entity type marker)","rank_in_archive_order":4,"of":9,"metrics":{"F1":"90.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}