{"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-and-relation-extraction-from","title":"Joint Entity and Relation Extraction from Scientific Documents: Role of Linguistic Information and Entity Types","arxiv_id":null,"date":"2021-09-30","proceeding":"Extraction and Evaluation of Knowledge Entities from Scientific Documents 2021 9","authors":["T Y S S Santosh","Prantika Chakraborty","Sudakshina Dutta","Debarshi Kumar Sanyal","Partha Pratim Das"],"abstract":"Scientific articles contain various types of domain-specific entities and relations between them. The entities and their relations\r\nsuccinctly capture important information about the topic of the\r\ndocument and hence, they are crucial to the understanding and\r\nautomatic analysis of the documents. In this paper, we aim to automatically extract entities and relations from a scientific abstract\r\nusing a deep neural model. Given an input sentence, we use a\r\npretrained transformer to produce contextual embeddings of the\r\ntokens which are then enriched with embeddings of their part-of-speech (POS) tags. A sequence of enriched token representations\r\nforms a span, and entities and relations are jointly learned over\r\nspans. Entity logits predicted by the entity classifier are used as\r\nfeatures in the relation classifier. Our proposed model improves\r\nupon competitive baselines in the literature for entity and relation\r\nextraction on SciERC and ADE datasets.","url_abs":"http://ceur-ws.org/Vol-3004/paper2.pdf","url_pdf":"http://ceur-ws.org/Vol-3004/paper2.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-and-relation-extraction-from","repo_url":"https://github.com/dksanyal/SpERT.PL","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"joint-entity-and-relation-extraction-on","task_name":"Joint Entity and Relation Extraction on Scientific Data"},{"task_slug":"pos","task_name":"POS"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/joint-entity-and-relation-extraction-on","task":"Joint Entity and Relation Extraction","dataset":"SciERC","model":"SpERT.PL (SciBERT)","rank_in_archive_order":3,"of":11,"metrics":{"Cross Sentence":"No","Entity F1":"70.53","Relation F1":"51.25"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"SpERT.PL (without overlap and BioBERT)","rank_in_archive_order":5,"of":15,"metrics":{"NER Macro F1":"91.14","RE+ Macro F1":"82.39"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"SpERT.PL (with overlap and BioBERT)","rank_in_archive_order":7,"of":15,"metrics":{"NER Macro F1":"91.17","RE+ Macro F1":"82.03"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}