{"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/span-based-joint-entity-and-relation","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","arxiv_id":"1909.07755","date":"2019-09-17","proceeding":null,"authors":["Markus Eberts","Adrian Ulges"],"abstract":"We introduce SpERT, an attention model for span-based joint entity and relation extraction. Our key contribution is a light-weight reasoning on BERT embeddings, which features entity recognition and filtering, as well as relation classification with a localized, marker-free context representation. The model is trained using strong within-sentence negative samples, which are efficiently extracted in a single BERT pass. These aspects facilitate a search over all spans in the sentence. In ablation studies, we demonstrate the benefits of pre-training, strong negative sampling and localized context. Our model outperforms prior work by up to 2.6% F1 score on several datasets for joint entity and relation extraction.","url_abs":"https://arxiv.org/abs/1909.07755v4","url_pdf":"https://arxiv.org/pdf/1909.07755v4.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":"span-based-joint-entity-and-relation","repo_url":"https://github.com/markus-eberts/spert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"span-based-joint-entity-and-relation","repo_url":"https://github.com/lavis-nlp/spert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"span-based-joint-entity-and-relation","repo_url":"https://github.com/yangyucheng000/Paper-3/tree/main/SpanQualifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/joint-entity-and-relation-extraction-on","task":"Joint Entity and Relation Extraction","dataset":"SciERC","model":"SpERT (with overlap)","rank_in_archive_order":4,"of":11,"metrics":{"Cross Sentence":"No","Entity F1":"70.3","Relation F1":"50.84"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on","task":"Joint Entity and Relation Extraction","dataset":"SciERC","model":"SpERT","rank_in_archive_order":9,"of":11,"metrics":{"Cross Sentence":"No","Entity F1":"70.33"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-scierc","task":"Named Entity Recognition (NER)","dataset":"SciERC","model":"SpERT","rank_in_archive_order":2,"of":7,"metrics":{"F1":"70.33"},"uses_additional_data":true},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"SpERT (without overlap)","rank_in_archive_order":11,"of":15,"metrics":{"NER Macro F1":"89.25","RE+ Macro F1":"79.24"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"SpERT (with overlap)","rank_in_archive_order":12,"of":15,"metrics":{"NER Macro F1":"89.28","RE+ Macro F1":"78.84"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-conll04","task":"Relation Extraction","dataset":"CoNLL04","model":"SpERT","rank_in_archive_order":3,"of":16,"metrics":{"NER Macro F1":"86.25","NER Micro F1":"88.94","RE+ Macro F1 ":"72.87","RE+ Micro F1":"71.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.07755","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}