{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:07:37Z","timestamp":1755839257384,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,1,8]]},"DOI":"10.1145\/3493700.3493707","type":"proceedings-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T23:54:21Z","timestamp":1641599661000},"page":"130-134","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Fine Grained Classification of Personal Data Entities with Language Models"],"prefix":"10.1145","author":[{"given":"Abhinav","family":"Nagpal","sequence":"first","affiliation":[{"name":"VIT Vellore, IN"}]},{"given":"Riddhiman","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, IN"}]},{"given":"Balaji","family":"Ganesan","sequence":"additional","affiliation":[{"name":"IBM Research, IN"}]}],"member":"320","published-online":{"date-parts":[[2022,1,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1075"},{"key":"e_1_3_2_1_2_1","volume-title":"Collective Learning From Diverse Datasets for Entity Typing in the Wild. 2446","author":"Abhishek Abhishek","year":"2019","unstructured":"Abhishek Abhishek, Amar\u00a0Prakash Azad, Balaji Ganesan, Ashish Anand, and Amit Awekar. 2019. Collective Learning From Diverse Datasets for Entity Typing in the Wild. 2446 (2019), 16\u201323."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341981.3344241"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics.","author":"Chiticariu Laura","year":"2010","unstructured":"Laura Chiticariu, Rajasekar Krishnamurthy, Yunyao Li, Sriram Raghavan, Frederick\u00a0R Reiss, and Shivakumar Vaithyanathan. 2010. SystemT: an algebraic approach to declarative information extraction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Eunsol Choi Omer Levy Yejin Choi and Luke Zettlemoyer. 2018. Ultra-Fine Entity Typing. arXiv preprint arXiv:1807.04905(2018). arxiv:1807.04905","DOI":"10.18653\/v1\/P18-1009"},{"key":"e_1_3_2_1_7_1","unstructured":"Riddhiman Dasgupta Balaji Ganesan Aswin Kannan Berthold Reinwald and Arun Kumar. 2018. Fine Grained Classification of Personal Data Entities. arxiv:1811.09368\u00a0[cs.CL]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw156"},{"key":"e_1_3_2_1_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278729"},{"key":"e_1_3_2_1_11_1","unstructured":"Dan Gillick Nevena Lazic Kuzman Ganchev Jesse Kirchner and David Huynh. 2014. Context-dependent fine-grained entity type tagging. arXiv preprint arXiv:1412.1820(2014). arxiv:1412.1820"},{"key":"e_1_3_2_1_12_1","unstructured":"Xiao Ling and Daniel\u00a0S Weld. 2012. Fine-Grained Entity Recognition.. In AAAI."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Federico L\u00f3pez and Michael Strube. 2020. A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification. arXiv preprint arXiv:2010.02053(2020). arxiv:2010.02053","DOI":"10.18653\/v1\/2020.findings-emnlp.42"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"John\u00a0X. Morris Eli Lifland Jin\u00a0Yong Yoo Jake Grigsby Di Jin and Yanjun Qi. 2020. TextAttack: A Framework for Adversarial Attacks Data Augmentation and Adversarial Training in NLP. arxiv:2005.05909\u00a0[cs.CL]","DOI":"10.18653\/v1\/2020.emnlp-demos.16"},{"key":"e_1_3_2_1_17_1","unstructured":"Shikhar Murty Patrick Verga Luke Vilnis and Andrew McCallum. 2017. Finer Grained Entity Typing with TypeNet. arXiv preprint arXiv:1711.05795(2017). arxiv:1711.05795"},{"key":"e_1_3_2_1_18_1","unstructured":"Yasumasa Onoe Michael Boratko and Greg Durrett. 2021. Modeling Fine-Grained Entity Types with Box Embeddings. arXiv preprint arXiv:2101.00345(2021). arxiv:2101.00345"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_1_20_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_21_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arxiv:1910.01108\u00a0[cs.CL]"},{"key":"e_1_3_2_1_22_1","unstructured":"Abhay\u00a0M Shalghar Ayush Kumar Balaji Ganesan Aswin Kannan and Shobha G. 2021. Document Structure aware Relational Graph Convolutional Networks for Ontology Population. arxiv:2104.12950\u00a0[cs.AI]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1119"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Lingraj\u00a0S Vannur Balaji Ganesan Lokesh Nagalapatti Hima Patel and MN Tippeswamy. 2021. Data Augmentation for Fairness in Personal Knowledge Base Population.. In PAKDD (Workshops). 143\u2013152.","DOI":"10.1007\/978-3-030-75015-2_15"},{"key":"e_1_3_2_1_25_1","volume-title":"RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information. arxiv:1812.04361\u00a0[cs.CL]","author":"Vashishth Shikhar","year":"2019","unstructured":"Shikhar Vashishth, Rishabh Joshi, Sai\u00a0Suman Prayaga, Chiranjib Bhattacharyya, and Partha Talukdar. 2019. RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information. arxiv:1812.04361\u00a0[cs.CL]"},{"key":"e_1_3_2_1_26_1","volume-title":"BBN pronoun coreference and entity type corpus","author":"Weischedel Ralph","year":"2005","unstructured":"Ralph Weischedel and Ada Brunstein. 2005. BBN pronoun coreference and entity type corpus. Linguistic Data Consortium, Philadelphia(2005)."},{"key":"e_1_3_2_1_27_1","volume-title":"Ontonotes release 5.0 ldc2013t19","author":"Weischedel Ralph","year":"2013","unstructured":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, 2013. Ontonotes release 5.0 ldc2013t19. Linguistic Data Consortium, Philadelphia, PA (2013)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Ji Xin Yankai Lin Zhiyuan Liu and Maosong Sun. 2018. Improving Neural Fine-Grained Entity Typing with Knowledge Attention. In AAAI.","DOI":"10.1609\/aaai.v32i1.12038"},{"key":"e_1_3_2_1_29_1","unstructured":"Peng Xu and Denilson Barbosa. 2018. Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss. arXiv preprint arXiv:1803.03378(2018)."},{"key":"e_1_3_2_1_30_1","unstructured":"Zhilin Yang Zihang Dai Yiming Yang Jaime Carbonell Ruslan Salakhutdinov and Quoc\u00a0V. Le. 2020. XLNet: Generalized Autoregressive Pretraining for Language Understanding. arxiv:1906.08237\u00a0[cs.CL]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2048"}],"event":{"name":"CODS-COMAD 2022: 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Bangalore India","acronym":"CODS-COMAD 2022"},"container-title":["Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3493700.3493707","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3493700.3493707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:51Z","timestamp":1750191111000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3493700.3493707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":31,"alternative-id":["10.1145\/3493700.3493707","10.1145\/3493700"],"URL":"https:\/\/doi.org\/10.1145\/3493700.3493707","relation":{},"subject":[],"published":{"date-parts":[[2022,1,8]]},"assertion":[{"value":"2022-01-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}