{"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/joint-entity-recognition-and-relation","title":"Joint entity recognition and relation extraction as a multi-head selection problem","arxiv_id":"1804.07847","date":"2018-04-20","proceeding":null,"authors":["Giannis Bekoulis","Johannes Deleu","Thomas Demeester","Chris Develder"],"abstract":"State-of-the-art models for joint entity recognition and relation extraction\nstrongly rely on external natural language processing (NLP) tools such as POS\n(part-of-speech) taggers and dependency parsers. Thus, the performance of such\njoint models depends on the quality of the features obtained from these NLP\ntools. However, these features are not always accurate for various languages\nand contexts. In this paper, we propose a joint neural model which performs\nentity recognition and relation extraction simultaneously, without the need of\nany manually extracted features or the use of any external tool. Specifically,\nwe model the entity recognition task using a CRF (Conditional Random Fields)\nlayer and the relation extraction task as a multi-head selection problem (i.e.,\npotentially identify multiple relations for each entity). We present an\nextensive experimental setup, to demonstrate the effectiveness of our method\nusing datasets from various contexts (i.e., news, biomedical, real estate) and\nlanguages (i.e., English, Dutch). Our model outperforms the previous neural\nmodels that use automatically extracted features, while it performs within a\nreasonable margin of feature-based neural models, or even beats them.","url_abs":"http://arxiv.org/abs/1804.07847v3","url_pdf":"http://arxiv.org/pdf/1804.07847v3.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":"joint-entity-recognition-and-relation","repo_url":"https://github.com/bekou/multihead_joint_entity_relation_extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"joint-entity-recognition-and-relation","repo_url":"https://github.com/Sanjithae/Joint_NER_RE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"joint-entity-recognition-and-relation","repo_url":"https://github.com/WindChimeRan/OpenJERE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"joint-entity-recognition-and-relation","repo_url":"https://github.com/btaille/sincere","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"joint-entity-recognition-and-relation","repo_url":"https://github.com/laloc2496/bert-jointly-relation-entity-extraciton","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"joint-entity-recognition-and-relation","repo_url":"https://github.com/mangonihao/MultiHeadJointEntityRelationExtraction_simple","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pos","task_name":"POS"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-ace-2004","task":"Relation Extraction","dataset":"ACE 2004","model":"multi-head","rank_in_archive_order":8,"of":11,"metrics":{"Cross Sentence":"No","NER Micro F1":"81.16","RE+ Micro F1":"47.14"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"multi-head","rank_in_archive_order":15,"of":15,"metrics":{"NER Macro F1":"86.40","RE+ Macro F1":"74.58"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-conll04","task":"Relation Extraction","dataset":"CoNLL04","model":"multi-head","rank_in_archive_order":7,"of":16,"metrics":{"NER Macro F1":"83.9","RE+ Macro F1 ":"62.04"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07847","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}