{"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/improving-distantly-supervised-relation-1","title":"Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention","arxiv_id":"1804.06987","date":"2018-04-19","proceeding":null,"authors":["Sharmistha Jat","Siddhesh Khandelwal","Partha Talukdar"],"abstract":"Relation extraction is the problem of classifying the relationship between\ntwo entities in a given sentence. Distant Supervision (DS) is a popular\ntechnique for developing relation extractors starting with limited supervision.\nWe note that most of the sentences in the distant supervision relation\nextraction setting are very long and may benefit from word attention for better\nsentence representation. Our contributions in this paper are threefold.\nFirstly, we propose two novel word attention models for distantly- supervised\nrelation extraction: (1) a Bi-directional Gated Recurrent Unit (Bi-GRU) based\nword attention model (BGWA), (2) an entity-centric attention model (EA), and\n(3) a combination model which combines multiple complementary models using\nweighted voting method for improved relation extraction. Secondly, we introduce\nGDS, a new distant supervision dataset for relation extraction. GDS removes\ntest data noise present in all previous distant- supervision benchmark\ndatasets, making credible automatic evaluation possible. Thirdly, through\nextensive experiments on multiple real-world datasets, we demonstrate the\neffectiveness of the proposed methods.","url_abs":"http://arxiv.org/abs/1804.06987v1","url_pdf":"http://arxiv.org/pdf/1804.06987v1.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":"improving-distantly-supervised-relation-1","repo_url":"https://github.com/CrisJk/PA-TRP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"improving-distantly-supervised-relation-1","repo_url":"https://github.com/JiyangZhang/learning-to-reweight-in-relation-extraion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improving-distantly-supervised-relation-1","repo_url":"https://github.com/SharmisthaJat/RE-DS-Word-Attention-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improving-distantly-supervised-relation-1","repo_url":"https://github.com/malllabiisc/RESIDE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"improving-distantly-supervised-relation-1","repo_url":"https://github.com/matnlp/hiclre","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"relationship-extraction-distant-supervised","task_name":"Relationship Extraction (Distant Supervised)"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relationship-extraction-distant-supervised-on","task":"Relationship Extraction (Distant Supervised)","dataset":"New York Times Corpus","model":"BGWA","rank_in_archive_order":4,"of":9,"metrics":{"P@10%":"70.9","P@30%":"52.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.06987","atlas_url":"https://app.syntology.ai/?focus=1804.06987","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}