{"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-distant-supervision-with-maxpooled","title":"Combining Distant and Direct Supervision for Neural Relation Extraction","arxiv_id":"1810.12956","date":"2018-10-30","proceeding":"NAACL 2019 6","authors":["Iz Beltagy","Kyle Lo","Waleed Ammar"],"abstract":"In relation extraction with distant supervision, noisy labels make it\ndifficult to train quality models. Previous neural models addressed this\nproblem using an attention mechanism that attends to sentences that are likely\nto express the relations. We improve such models by combining the distant\nsupervision data with an additional directly-supervised data, which we use as\nsupervision for the attention weights. We find that joint training on both\ntypes of supervision leads to a better model because it improves the model's\nability to identify noisy sentences. In addition, we find that sigmoidal\nattention weights with max pooling achieves better performance over the\ncommonly used weighted average attention in this setup. Our proposed method\nachieves a new state-of-the-art result on the widely used FB-NYT dataset.","url_abs":"http://arxiv.org/abs/1810.12956v2","url_pdf":"http://arxiv.org/pdf/1810.12956v2.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-distant-supervision-with-maxpooled","repo_url":"https://github.com/allenai/comb_dist_direct_relex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12956","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}