{"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/multi-multi-view-learning-multilingual-and","title":"Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing","arxiv_id":"1810.10499","date":"2018-10-24","proceeding":"EMNLP 2018 10","authors":["Yadollah Yaghoobzadeh","Hinrich Schütze"],"abstract":"Knowledge bases (KBs) are paramount in NLP. We employ multiview learning for\nincreasing accuracy and coverage of entity type information in KBs. We rely on\ntwo metaviews: language and representation. For language, we consider\nhigh-resource and low-resource languages from Wikipedia. For representation, we\nconsider representations based on the context distribution of the entity (i.e.,\non its embedding), on the entity's name (i.e., on its surface form) and on its\ndescription in Wikipedia. The two metaviews language and representation can be\nfreely combined: each pair of language and representation (e.g., German\nembedding, English description, Spanish name) is a distinct view. Our\nexperiments on entity typing with fine-grained classes demonstrate the\neffectiveness of multiview learning. We release MVET, a large multiview - and,\nin particular, multilingual - entity typing dataset we created. Mono- and\nmultilingual fine-grained entity typing systems can be evaluated on this\ndataset.","url_abs":"http://arxiv.org/abs/1810.10499v1","url_pdf":"http://arxiv.org/pdf/1810.10499v1.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":"multi-multi-view-learning-multilingual-and","repo_url":"https://github.com/yyaghoobzadeh/MVET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"multi-view-learning","task_name":"MULTI-VIEW LEARNING"},{"task_slug":"multiview-learning","task_name":"Multiview Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}