{"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/from-bag-of-sentences-to-document-distantly","title":"From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension","arxiv_id":"2012.04334","date":"2020-12-08","proceeding":null,"authors":["Lingyong Yan","Xianpei Han","Le Sun","Fangchao Liu","Ning Bian"],"abstract":"Distant supervision (DS) is a promising approach for relation extraction but often suffers from the noisy label problem. Traditional DS methods usually represent an entity pair as a bag of sentences and denoise labels using multi-instance learning techniques. The bag-based paradigm, however, fails to leverage the inter-sentence-level and the entity-level evidence for relation extraction, and their denoising algorithms are often specialized and complicated. In this paper, we propose a new DS paradigm--document-based distant supervision, which models relation extraction as a document-based machine reading comprehension (MRC) task. By re-organizing all sentences about an entity as a document and extracting relations via querying the document with relation-specific questions, the document-based DS paradigm can simultaneously encode and exploit all sentence-level, inter-sentence-level, and entity-level evidence. Furthermore, we design a new loss function--DSLoss (distant supervision loss), which can effectively train MRC models using only $\\langle$document, question, answer$\\rangle$ tuples, therefore noisy label problem can be inherently resolved. Experiments show that our method achieves new state-of-the-art DS performance.","url_abs":"https://arxiv.org/abs/2012.04334v2","url_pdf":"https://arxiv.org/pdf/2012.04334v2.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":"from-bag-of-sentences-to-document-distantly","repo_url":"https://github.com/lingyongyan/docds","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"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":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relationship-extraction-distant-supervised-on-2","task":"Relationship Extraction (Distant Supervised)","dataset":"NYT","model":"DocDS","rank_in_archive_order":1,"of":1,"metrics":{"P@100":"0.939","P@200":"0.889","P@300":"0.873","PR AUC":"0.595"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}