{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:52:30Z","timestamp":1773481950338,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"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":[[2022,6,10]]},"DOI":"10.1145\/3514221.3526049","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"2259-2272","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Saga: A Platform for Continuous Construction and Serving of Knowledge at Scale"],"prefix":"10.1145","author":[{"given":"Ihab F.","family":"Ilyas","sequence":"first","affiliation":[{"name":"Apple, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodoros","family":"Rekatsinas","sequence":"additional","affiliation":[{"name":"Apple, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishnu","family":"Konda","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey","family":"Pound","sequence":"additional","affiliation":[{"name":"Apple, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Qi","sequence":"additional","affiliation":[{"name":"Apple, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Soliman","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"JSON for linking data. https:\/\/json-ld.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_3_1","volume-title":"Managing and mining graph data","author":"Aggarwal Charu C","unstructured":"Charu C Aggarwal and Haixun Wang. 2010. Graph data management and mining: A survey of algorithms and applications. In Managing and mining graph data. Springer, 13--68."},{"key":"e_1_3_2_1_4_1","unstructured":"Mohammad Al Hasan Vineet Chaoji Saeed Salem and Mohammed Zaki. Link prediction using supervised learning."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1322432.1322433"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of ACL-08: HLT. 28--36","author":"Banko Michele","year":"2008","unstructured":"Michele Banko and Oren Etzioni. 2008. The tradeoffs between open and traditional relation extraction. In Proceedings of ACL-08: HLT. 28--36."},{"key":"e_1_3_2_1_7_1","volume-title":"Collective entity resolution in relational data. ACM Transactions on Knowledge Discovery from Data (TKDD) 1, 1","author":"Bhattacharya Indrajit","year":"2007","unstructured":"Indrajit Bhattacharya and Lise Getoor. 2007. Collective entity resolution in relational data. ACM Transactions on Knowledge Discovery from Data (TKDD) 1, 1 (2007), 5--es."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956759"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems -","volume":"2","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Dur\u00e1n, Jason Weston, and Oksana Yakhnenko. 2013. Translating Embeddings for Modeling Multi-Relational Data. In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2 (Lake Tahoe, Nevada) (NIPS'13). Curran Associates Inc., Red Hook, NY, USA, 2787\u00e2??2795."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Sergey Brin and Lawrence Page. 1998. The Anatomy of a Large-Scale Hyper-textual Web Search Engine. In COMPUTER NETWORKS AND ISDN SYSTEMS. 107--117.","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2894748"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"e_1_3_2_1_14_1","volume-title":"VLDB","volume":"86","author":"Chakravarthy Upen S","year":"1986","unstructured":"Upen S Chakravarthy and Jack Minker. 1986. Multiple Query Processing in Deductive Databases using Query Graphs.. In VLDB, Vol. 86. Citeseer, 384--391."},{"key":"e_1_3_2_1_15_1","volume-title":"Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. arXiv preprint arXiv:1611.03954","author":"Chen Muhao","year":"2016","unstructured":"Muhao Chen, Yingtao Tian, Mohan Yang, and Carlo Zaniolo. 2016. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. arXiv preprint arXiv:1611.03954 (2016)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_17_1","volume-title":"IIWeb","volume":"3","author":"Cohen William W","year":"2003","unstructured":"William W Cohen, Pradeep Ravikumar, Stephen E Fienberg, et al. 2003. A Comparison of String Distance Metrics for Name-Matching Tasks.. In IIWeb, Vol. 3. Citeseer, 73--78."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559795.1559797"},{"key":"e_1_3_2_1_19_1","first-page":"1","article-title":"DeepDive","volume":"45","author":"Sa Christopher De","year":"2016","unstructured":"Christopher De Sa, Alex Ratner, Christopher R\u00e9, Jaeho Shin, Feiran Wang, Sen Wu, and Ce Zhang. 2016. DeepDive: Declarative Knowledge Base Construction. SIGMOD Rec. 45, 1 (June 2016), 60\u00e267.","journal-title":"Declarative Knowledge Base Construction. SIGMOD Rec."},{"key":"e_1_3_2_1_20_1","volume-title":"Ives","author":"Doan AnHai","year":"2012","unstructured":"AnHai Doan, Alon Y. Halevy, and Zachary G. Ives. 2012. Principles of Data Integration."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3405476"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623623"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219938"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687690"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/2777598.2777603"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687620"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544914"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2814710.2814713"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2594511"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988687"},{"key":"e_1_3_2_1_31_1","volume-title":"Adalbert Gerald Soosai Raj, and Jignesh M Patel","author":"Fan Jing","year":"2015","unstructured":"Jing Fan, Adalbert Gerald Soosai Raj, and Jignesh M Patel. 2015. The Case Against Specialized Graph Analytics Engines.. In CIDR."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174047"},{"key":"e_1_3_2_1_33_1","volume-title":"Building a large-scale, accurate and fresh knowledge graph. KDD-","author":"Gao Yuqing","year":"2018","unstructured":"Yuqing Gao, Jisheng Liang, Benjamin Han, Mohamed Yakout, and Ahmed Mohamed. 2018. Building a large-scale, accurate and fresh knowledge graph. KDD- 2018, Tutorial 39 (2018), 1939--1374."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295241"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3115\/992628.992709"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732939.2732943"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_3_2_1_39_1","volume-title":"Record fusion: A learning approach. arXiv preprint arXiv:2006.10208","author":"Heidari Alireza","year":"2020","unstructured":"Alireza Heidari, George Michalopoulos, Shrinu Kushagra, Ihab F Ilyas, and Theodoros Rekatsinas. 2020. Record fusion: A learning approach. arXiv preprint arXiv:2006.10208 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Ihab F Ilyas and Xu Chu. 2019. Data cleaning. Morgan & Claypool.","DOI":"10.1145\/3310205"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733057"},{"key":"e_1_3_2_1_42_1","volume-title":"Ava: From Data to Insights Through Conversations.. In CIDR.","author":"Leo John Rogers Jeffrey","year":"2017","unstructured":"Rogers Jeffrey Leo John, Navneet Potti, and Jignesh M Patel. 2017. Ava: From Data to Insights Through Conversations.. In CIDR."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016285"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142599"},{"key":"e_1_3_2_1_45_1","volume-title":"Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360","author":"Lample Guillaume","year":"2016","unstructured":"Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 (2016)."},{"key":"e_1_3_2_1_46_1","unstructured":"Ora Lassila Ralph R Swick et al. 1998. Resource description framework (RDF) model and syntax specification. (1998)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.3233\/SW-140134"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/543613.543644"},{"key":"e_1_3_2_1_49_1","volume-title":"PyTorch-BigGraph: A Large-scale Graph Embedding System. CoRR abs\/1903.12287","author":"Lerer Adam","year":"2019","unstructured":"Adam Lerer, Ledell Wu, Jiajun Shen, Timoth\u00e9e Lacroix, Luca Wehrstedt, Abhijit Bose, and Alexander Peysakhovich. 2019. PyTorch-BigGraph: A Large-scale Graph Embedding System. CoRR abs\/1903.12287 (2019). arXiv:1903.12287 http:\/\/arxiv.org\/abs\/1903.12287"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897350.2897352"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886624"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1200"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/1690219.1690287"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"T. Mitchell W. Cohen E. Hruscha P. Talukdar J. Betteridge A. Carlson B. Dalvi M. Gardner B. Kisiel J. Krishnamurthy N. Lao K. Mazaitis T. Mohammad N. Nakashole E. Platanios A. Ritter M. Samadi B. Settles R. Wang D. Wijaya A. Gupta X. Chen A. Saparov M. Greaves and J. Welling. 2015. Never-Ending Learning. In AAAI. http:\/\/www.cs.cmu.edu\/~wcohen\/pubs.html : Never-Ending Learning in AAAI-2015.","DOI":"10.1609\/aaai.v29i1.9498"},{"key":"e_1_3_2_1_55_1","volume-title":"End-to-end relation extraction using lstms on sequences and tree structures. arXiv preprint arXiv:1601.00770","author":"Miwa Makoto","year":"2016","unstructured":"Makoto Miwa and Mohit Bansal. 2016. End-to-end relation extraction using lstms on sequences and tree structures. arXiv preprint arXiv:1601.00770 (2016)."},{"key":"e_1_3_2_1_56_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021","author":"Mohoney Jason","year":"2021","unstructured":"Jason Mohoney, Roger Waleffe, Henry Xu, Theodoros Rekatsinas, and Shivaram Venkataraman. 2021. Marius: Learning Massive Graph Embeddings on a Single Machine. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021, July 14--16, 2021, Angela Demke Brown and Jay R. Lorch (Eds.). USENIX Association, 533--549."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196926"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412159"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"e_1_3_2_1_60_1","volume-title":"Aida-light: High-throughput named-entity disambiguation. In LDOW.","author":"Nguyen Dat Ba","year":"2014","unstructured":"Dat Ba Nguyen, Johannes Hoffart, Martin Theobald, and Gerhard Weikum. 2014. Aida-light: High-throughput named-entity disambiguation. In LDOW."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331166"},{"key":"e_1_3_2_1_62_1","volume-title":"Bootleg: Chasing the tail with self-supervised named entity disambiguation. CIDR","author":"Orr Laurel","year":"2021","unstructured":"Laurel Orr, Megan Leszczynski, Simran Arora, Sen Wu, Neel Guha, Xiao Ling, and Christopher Re. 2021. Bootleg: Chasing the tail with self-supervised named entity disambiguation. CIDR (2021)."},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems -","volume":"1","author":"Pan Xinghao","unstructured":"Xinghao Pan, Dimitris Papailiopoulos, Samet Oymak, Benjamin Recht, Kannan Ramchandran, and Michael I. Jordan. 2015. Parallel Correlation Clustering on Big Graphs. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS'15). MIT Press, Cambridge, MA, USA, 82\u00e290."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377455"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/1938545.1938546"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035951"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66917-5_19"},{"key":"e_1_3_2_1_69_1","volume-title":"Davis","author":"Salehpour Masoud","year":"2020","unstructured":"Masoud Salehpour and Joseph G. Davis. 2020. The Effects of Different JSON Representations on Querying Knowledge Graphs. CoRR abs\/2004.04286 (2020). arXiv:2004.04286 https:\/\/arxiv.org\/abs\/2004.04286"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/16894.16874"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3058739"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11257-2_20"},{"key":"e_1_3_2_1_73_1","volume-title":"Cidr","volume":"2013","author":"Stonebraker Michael","year":"2013","unstructured":"Michael Stonebraker, Daniel Bruckner, Ihab F Ilyas, George Beskales, Mitch Cherniack, Stanley B Zdonik, Alexander Pagan, and Shan Xu. 2013. Data Curation at Scale: The Data Tamer System.. In Cidr, Vol. 2013."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.14778\/2021017.2021020"},{"key":"e_1_3_2_1_78_1","volume-title":"WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset. CoRR abs\/2107.09556","author":"Wang Luyu","year":"2021","unstructured":"Luyu Wang, Yujia Li, \u00d6zlem Aslan, and Oriol Vinyals. 2021. WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset. CoRR abs\/2107.09556 (2021). arXiv:2107.09556 https:\/\/arxiv.org\/abs\/2107.09556"},{"key":"e_1_3_2_1_79_1","volume-title":"Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196","author":"Wei Jason","year":"2019","unstructured":"Jason Wei and Kai Zou. 2019. Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000064"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559870"},{"key":"e_1_3_2_1_82_1","first-page":"307","article-title":"Attention-based Learning for Missing Data Imputation in HoloClean","volume":"2","author":"Wu Richard","year":"2020","unstructured":"Richard Wu, Aoqian Zhang, Ihab Ilyas, and Theodoros Rekatsinas. 2020. Attention-based Learning for Missing Data Imputation in HoloClean. In Proceedings of Machine Learning and Systems, Vol. 2. 307--325.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_83_1","volume-title":"Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities. arXiv: Computation and Language","author":"Yamada Ikuya","year":"2019","unstructured":"Ikuya Yamada, Koki Washio, Hiroyuki Shindo, and Yuji Matsumoto. 2019. Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities. arXiv: Computation and Language (2019)."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386143"},{"key":"e_1_3_2_1_85_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Yang Bishan","year":"2015","unstructured":"Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401172"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223848"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526049","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:07Z","timestamp":1750183807000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":88,"alternative-id":["10.1145\/3514221.3526049","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3526049","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}