{"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/distant-supervision-relation-extraction-with","title":"Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions","arxiv_id":"1904.00143","date":"2019-03-30","proceeding":"NAACL 2019 6","authors":["Zhi-Xiu Ye","Zhen-Hua Ling"],"abstract":"This paper presents a neural relation extraction method to deal with the\nnoisy training data generated by distant supervision. Previous studies mainly\nfocus on sentence-level de-noising by designing neural networks with intra-bag\nattentions. In this paper, both intra-bag and inter-bag attentions are\nconsidered in order to deal with the noise at sentence-level and bag-level\nrespectively. First, relation-aware bag representations are calculated by\nweighting sentence embeddings using intra-bag attentions. Here, each possible\nrelation is utilized as the query for attention calculation instead of only\nusing the target relation in conventional methods. Furthermore, the\nrepresentation of a group of bags in the training set which share the same\nrelation label is calculated by weighting bag representations using a\nsimilarity-based inter-bag attention module. Finally, a bag group is utilized\nas a training sample when building our relation extractor. Experimental results\non the New York Times dataset demonstrate the effectiveness of our proposed\nintra-bag and inter-bag attention modules. Our method also achieves better\nrelation extraction accuracy than state-of-the-art methods on this dataset.","url_abs":"http://arxiv.org/abs/1904.00143v1","url_pdf":"http://arxiv.org/pdf/1904.00143v1.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":"distant-supervision-relation-extraction-with","repo_url":"https://github.com/ZhixiuYe/Intra-Bag-and-Inter-Bag-Attentions","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"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00143","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}