{"type":"ScholarlyArticle","title":"Modeling Noisy Hierarchical Types in Fine-Grained Entity Typing: A Content-Based Weighting Approach","authors":[{"name":"Junshuang Wu","slug":"junshuang-wu","given":"Junshuang","family":"Wu","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China; Beijing Advanced Institution on Big Data and Brain Computing , Beihang University , Beijing , China"},{"name":"Richong Zhang","slug":"richong-zhang","given":"Richong","family":"Zhang","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China; Beijing Advanced Institution on Big Data and Brain Computing , Beihang University , Beijing , China"},{"name":"Yongyi Mao","slug":"yongyi-mao","given":"Yongyi","family":"Mao","affiliation":"School of Electrical Engineering and Computer Science , University of Ottawa , Ottawa , Canada"},{"name":"Hongyu Guo","slug":"hongyu-guo","given":"Hongyu","family":"Guo","affiliation":"National Research Council Canada , Ottawa , Canada"},{"name":"Jinpeng Huai","slug":"jinpeng-huai","given":"Jinpeng","family":"Huai","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China; Beijing Advanced Institution on Big Data and Brain Computing , Beihang University , Beijing , China"}],"abstract":"Fine-grained entity typing (FET), which annotates the entities in a sentence with a set of finely specified type labels, often serves as the first and critical step towards many natural language processing tasks. Despite great processes have been made, current FET methods have difficulty to cope with the noisy labels which naturally come with the data acquisition processes. Existing FET approaches either pre-process to clean the noise or simply focus on one of the noisy labels, sidestepping the fact that those noises are related and content dependent. In this paper, we directly model the structured, noisy labels with a novel content-sensitive weighting schema. Coupled with a newly devised cost function and a hierarchical type embedding strategy, our method leverages a random walk process to effectively weight out noisy labels during training. Experiments on several benchmark datasets validate the effectiveness of the proposed framework and establish it as a new state of the art strategy for noisy entity typing problem.","doi":"10.24963/ijcai.2019/731","url":"https://ijcai.org/proceedings/2019/731","pdf":"https://ijcai.org/proceedings/2019/0731.pdf","markdown":"https://ijcai.org/proceedings/2019/731.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/731","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":731,"pages":{"first":5264,"last":5270},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: NLP Applications and Tools"],"videos":[],"references":[{"position":1,"raw":"[Abhishek et al., 2017] Abhishek, Ashish Anand, and Amit Awekar. Fine-grained entity type classification by jointly learning representations and label embeddings. In Pro- ceedings of EACL, pages 797-807, 2017.","title":"Fine-grained entity type classification by jointly learning representations and label embeddings","authors":"Ashish Abhishek, Amit Anand, Awekar","year":"2017","venue":"Proceedings of EACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Dong et al., 2014] Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, and Wei Zhang. Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In KDD, pages 601-610, 2014.","title":"Knowledge vault: a web-scale approach to probabilistic knowledge fusion","authors":"Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, Wei Zhang","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dong et al., 2015] Li Dong, Furu Wei, Hong Sun, Ming Zhou, and Ke Xu. A hybrid neural model for type classifi- cation of entity mentions. In Proceedings of IJCAI, pages 1243-1249, 2015.","title":"A hybrid neural model for type classification of entity mentions","authors":"Li Dong, Furu Wei, Hong Sun, Ming Zhou, Ke Xu","year":"2015","venue":"Proceedings of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/179"},{"position":4,"raw":"[Gillick et al., 2014] Dan Gillick, Nevena Lazic, Kuzman Ganchev, Jesse Kirchner, and David Huynh. Context- dependent fine-grained entity type tagging. arXiv preprint arXiv:1412.1820, 2014.","title":"Contextdependent fine-grained entity type tagging","authors":"Dan Gillick, Nevena Lazic, Kuzman Ganchev, Jesse Kirchner, David Huynh","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Koch et al., 2014] Mitchell Koch, John Gilmer, Stephen Soderland, and Daniel S. Weld. Type-aware distantly su- pervised relation extraction with linked arguments. In Pro- ceedings of EMNLP, pages 1891-1901, 2014.","title":"Type-aware distantly supervised relation extraction with linked arguments","authors":"Mitchell Koch, John Gilmer, Stephen Soderland, Daniel S Weld","year":"2014","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ling and Weld, 2012] Xiao Ling and Daniel S. Weld. Fine- grained entity recognition. In Proceedings of AAAI, 2012.","title":"Finegrained entity recognition","authors":"Xiao Ling, Daniel S Weld","year":"2012","venue":"Proceedings of AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ling et al., 2015] Xiao Ling, Sameer Singh, and Daniel S. Weld. Design challenges for entity linking. TACL, 3:315- 328, 2015.","title":"Design challenges for entity linking","authors":"Xiao Ling, Sameer Singh, Daniel S Weld","year":"2015","venue":"TACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2014] Yang Liu, Kang Liu, Liheng Xu, and Jun Zhao. Exploring fine-grained entity type constraints for distantly supervised relation extraction. In Proceedings of COLING, pages 2107-2116, 2014.","title":"Exploring fine-grained entity type constraints for distantly supervised relation extraction","authors":"Yang Liu, Kang Liu, Liheng Xu, Jun Zhao","year":"2014","venue":"Proceedings of COLING","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ma et al., 2016] Yukun Ma, Erik Cambria, and Sa Gao. La- bel embedding for zero-shot fine-grained named entity typing. In Proceedings of COLING, pages 171-180, 2016.","title":"Label embedding for zero-shot fine-grained named entity typing","authors":"Yukun Ma, Erik Cambria, Sa Gao","year":"2016","venue":"Proceedings of COLING","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[McCallum et al., 2018] Andrew McCallum, Patrick Verga, Luke Vilnis, Shikhar Murty, and Irena Radovanovic. Hi- erarchical losses and new resources for fine-grained entity typing and linking. In Proceedings of ACL, pages 97-109. ACL, 2018.","title":"Hierarchical losses and new resources for fine-grained entity typing and linking","authors":"Andrew Mccallum, Patrick Verga, Luke Vilnis, Shikhar Murty, Irena Radovanovic","year":"2018","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mintz et al., 2009] Mike Mintz, Steven Bills, Rion Snow, and D aniel Jurafsky. Distant supervision for relation ex- traction without labeled data. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 1003-1011, 2009.","title":"Distant supervision for relation extraction without labeled data","authors":"Mike Mintz, Steven Bills, Rion Snow, Jurafsky","year":"2009","venue":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. Glove: Global vectors for word representation. In Proceedings of EMNLP, pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher D Manning","year":"2014","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ren et al., 2016a] Xiang Ren, Wenqi He, Meng Qu Lifu Huang, Heng Ji, and Jiawei Han. AFET: automatic fine- grained entity typing by hierarchical partial-label embed- ding. In Proceedings of EMNLP, pages 1369-1378, 2016.","title":"AFET: automatic finegrained entity typing by hierarchical partial-label embedding","authors":"Ren","year":"2016","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ren et al., 2016b] Xiang Ren, Wenqi He, Meng Qu, Clare R. Voss, Heng Ji, and Jiawei Han. Label noise re- duction in entity typing by heterogeneous partial-label em- bedding. In Proceedings of KDD, pages 1825-1834, 2016.","title":"Label noise reduction in entity typing by heterogeneous partial-label embedding","authors":"Ren","year":"2016","venue":"Proceedings of KDD","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Shimaoka et al., 2017] Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, and Sebastian Riedel. Neural architectures for fine-grained entity type classification. In Proceedings of EACL, pages 1271-1280, 2017.","title":"Neural architectures for fine-grained entity type classification","authors":"Shimaoka","year":"2017","venue":"Proceedings of EACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Weischedel and Brunstein, 2015] Ralph Weischedel and Ada Brunstein. Bbn pronoun coreference and entity type corpus. page 112, 2015.","title":"Bbn pronoun coreference and entity type corpus","authors":"Brunstein Weischedel, Ralph Weischedel, Ada Brunstein","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Weischedel et al., 2011] Ralph Weischedel, Eduard Hovy, Mitchell Marcus, Martha Palmer, Robert Belvin, Sameer Pradhan, Lance Ramshaw, and Nianwen Xue. Ontonotes: A large training corpus for enhanced processing. 2011.","title":"Ontonotes: A large training corpus for enhanced processing","authors":"Ralph Weischedel, Eduard Hovy, Mitchell Marcus, Martha Palmer, Robert Belvin, Sameer Pradhan, Lance Ramshaw, Nianwen Xue","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Xin et al., 2018] Ji Xin, Yankai Lin, Zhiyuan Liu, and Maosong Sun. Improving neural fine-grained entity typ- ing with knowledge attention. In Proceedings of AAAI, 2018.","title":"Improving neural fine-grained entity typing with knowledge attention","authors":"Ji Xin, Yankai Lin, Zhiyuan Liu, Maosong Sun","year":"2018","venue":"Proceedings of AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xu and Barbosa, 2018] Peng Xu and Denilson Barbosa. Neural fine-grained entity type classification with hierarchy-aware loss. In Proceedings of NAACL. ACL, June 2018.","title":"Neural fine-grained entity type classification with hierarchy-aware loss","authors":"Peng Xu, Denilson Barbosa","year":"2018","venue":"Proceedings of NAACL. ACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yogatama et al., 2015] Dani Yogatama, Daniel Gillick, and Nevena Lazic. Embedding methods for fine grained entity type classification. In Proceedings of ACL, pages 291-296. ACL, 2015.","title":"Embedding methods for fine grained entity type classification","authors":"Dani Yogatama, Daniel Gillick, Nevena Lazic","year":"2015","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yosef et al., 2012] Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart, Marc Spaniol, and Gerhard Weikum. Hyena: Hierarchical type classification for entity names. In Proceedings of COLING 2012: Posters, pages 1361- 1370, 2012.","title":"Hyena: Hierarchical type classification for entity names","authors":"Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart, Marc Spaniol, Gerhard Weikum","year":"2012","venue":"Proceedings of COLING 2012: Posters","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}