{"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/mgsohrab-at-wnut-2020-shared-task-1-neural","title":"mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols","arxiv_id":null,"date":"2020-11-01","proceeding":"Workshop on Noisy User-generated Text 2020 11","authors":["Mohammad Golam Sohrab","Anh-Khoa Duong Nguyen","Makoto Miwa","Hiroya Takamura"],"abstract":"We present a neural exhaustive approach that\r\naddresses named entity recognition (NER) and\r\nrelation recognition (RE), for the entity and relation recognition over the wet-lab protocols\r\nshared task. We introduce BERT-based neural\r\nexhaustive approach that enumerates all possible spans as potential entity mentions and\r\nclassifies them into entity types or no entity\r\nwith deep neural networks to address NER.\r\nTo solve relation extraction task, based on the\r\nNER predictions or given gold mentions we\r\ncreate all possible trigger-argument pairs and\r\nclassify them into relation types or no relation.\r\nIn NER task, we achieved 76.60% in terms of\r\nF-score as third rank system among the participated systems. In relation extraction task, we\r\nachieved 80.46% in terms of F-score as the top\r\nsystem in the relation extraction or recognition\r\ntask. Besides we compare our model based on\r\nthe wet lab protocols corpus (WLPC) with the\r\nWLPC baseline and dynamic graph-based information extraction (DyGIE) systems.","url_abs":"https://aclanthology.org/2020.wnut-1.38","url_pdf":"https://aclanthology.org/2020.wnut-1.38.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":"mgsohrab-at-wnut-2020-shared-task-1-neural","repo_url":"https://github.com/dnanhkhoa/WNUT-2020","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-on-wnut-20-task-1","task":"Named Entity Recognition (NER)","dataset":"WNUT 2020","model":"mgsohrab","rank_in_archive_order":1,"of":3,"metrics":{"F1":"76.60"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}