{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:54:13Z","timestamp":1786636453563,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T00:00:00Z","timestamp":1528761600000},"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":[[2018,6,12]]},"DOI":"10.1145\/3205289.3205325","type":"proceedings-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T12:54:52Z","timestamp":1536843292000},"page":"195-206","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Zwift"],"prefix":"10.1145","author":[{"given":"Feng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Data Engineering and Knowledge Engineering (Renmin University of China), MOE, China, School of Information, Renmin University of China, China and Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"Computer Science Department, North Carolina State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/dumps.wikimedia.org\/enwiki\/","author":"Wikipedia HTML","year":"2017","unstructured":"Wikipedia HTML data dumps. https:\/\/dumps.wikimedia.org\/enwiki\/ , 2017 . Wikipedia HTML data dumps. https:\/\/dumps.wikimedia.org\/enwiki\/, 2017."},{"key":"e_1_3_2_1_2_1","volume-title":"NSDI","author":"Agarwal Rachit","year":"2015","unstructured":"Rachit Agarwal , Anurag Khandelwal , and Ion Stoica . Succinct : Enabling Queries on Compressed Data . In NSDI , 2015 . Rachit Agarwal, Anurag Khandelwal, and Ion Stoica. Succinct: Enabling Queries on Compressed Data. In NSDI, 2015."},{"key":"e_1_3_2_1_3_1","volume-title":"PUMA: Purdue MapReduce Benchmarks Suite","author":"Ahmad Faraz","year":"2012","unstructured":"Faraz Ahmad , Seyong Lee , Mithuna Thottethodi , and TN Vijaykumar . PUMA: Purdue MapReduce Benchmarks Suite . 2012 . Faraz Ahmad, Seyong Lee, Mithuna Thottethodi, and TN Vijaykumar. PUMA: Purdue MapReduce Benchmarks Suite. 2012."},{"key":"e_1_3_2_1_4_1","volume-title":"Amazon Elastic Compute Cloud","year":"2009","unstructured":"Amazon. Amazon Elastic Compute Cloud . 2009 . Amazon. Amazon Elastic Compute Cloud. 2009."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367673"},{"key":"e_1_3_2_1_8_1","volume-title":"HDFS Architecture Guide. Hadoop Apache Project","author":"Dhruba","year":"2008","unstructured":"Dhruba Borthakur et al . HDFS Architecture Guide. Hadoop Apache Project , 2008 . Dhruba Borthakur et al. HDFS Architecture Guide. Hadoop Apache Project, 2008."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/96749.98245"},{"key":"e_1_3_2_1_10_1","volume-title":"Content-aware Partial Compression for Textual Big Data Analysis in Hadoop","author":"Dong Dapeng","year":"2017","unstructured":"Dapeng Dong and John Herbert . Content-aware Partial Compression for Textual Big Data Analysis in Hadoop . IEEE Transactions on Big Data , 2017 . Dapeng Dong and John Herbert. Content-aware Partial Compression for Textual Big Data Analysis in Hadoop. IEEE Transactions on Big Data, 2017."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751236"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009761603038"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19294-4_9"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1173706.1173744"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-72253-0_63"},{"key":"e_1_3_2_1_16_1","unstructured":"M. Lichman. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml 2013.  M. Lichman. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml 2013."},{"key":"e_1_3_2_1_17_1","volume-title":"KDD","author":"Monge Alvaro E","year":"1996","unstructured":"Alvaro E Monge , Charles Elkan , The field matching problem: Algorithms and applications . In KDD , 1996 . Alvaro E Monge, Charles Elkan, et al. The field matching problem: Algorithms and applications. In KDD, 1996."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/375360.375365"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3092586"},{"key":"e_1_3_2_1_20_1","volume-title":"Journal of Artificial Intelligence Research","author":"Craig","year":"1997","unstructured":"Craig G. Nevill-Manning and Ian H. Witten. Identifying Hierarchical Structure in Sequences: A linear-time algorithm . Journal of Artificial Intelligence Research , 1997 . Craig G. Nevill-Manning and Ian H. Witten. Identifying Hierarchical Structure in Sequences: A linear-time algorithm. Journal of Artificial Intelligence Research, 1997."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"e_1_3_2_1_22_1","volume-title":"Linguistic Inquiry and Word Count: LIWC","author":"Pennebaker James W","year":"2001","unstructured":"James W Pennebaker , Martha E Francis , and Roger J Booth . Linguistic Inquiry and Word Count: LIWC 2001 . Mahway : Lawrence Erlbaum Associates , 2001. James W Pennebaker, Martha E Francis, and Roger J Booth. Linguistic Inquiry and Word Count: LIWC 2001. Mahway: Lawrence Erlbaum Associates, 2001."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_24_1","volume-title":"VLDB","author":"Raman Vijayshankar","year":"2001","unstructured":"Vijayshankar Raman and Joseph M Hellerstein . Potter's Wheel : An Interactive Data Cleaning System . In VLDB , 2001 . Vijayshankar Raman and Joseph M Hellerstein. Potter's Wheel: An Interactive Data Cleaning System. In VLDB, 2001."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775087"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1456469.1456471"},{"key":"e_1_3_2_1_28_1","volume-title":"Big Data","author":"Vandierendonck Hans","year":"2016","unstructured":"Hans Vandierendonck , Karen Murphy , Mahwish Arif , and Dimitrios S Nikolopoulos . HPTA : High-performance text analytics . In Big Data , 2016 . Hans Vandierendonck, Karen Murphy, Mahwish Arif, and Dimitrios S Nikolopoulos. HPTA: High-performance text analytics. In Big Data, 2016."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526764"},{"key":"e_1_3_2_1_30_1","volume-title":"HotCloud","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J Franklin , Scott Shenker , and Ion Stoica . Spark : Cluster Computing with Working Sets . HotCloud , 2010 . Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. Spark: Cluster Computing with Working Sets. HotCloud, 2010."},{"key":"e_1_3_2_1_31_1","volume-title":"Lexical acquisition: exploiting online resources to build a lexicon","author":"Zernik Uri","year":"1991","unstructured":"Uri Zernik . Lexical acquisition: exploiting online resources to build a lexicon . Psychology Press , 1991 . Uri Zernik. Lexical acquisition: exploiting online resources to build a lexicon. Psychology Press, 1991."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3049832.3049836"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470454"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123978"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"}],"event":{"name":"ICS '18: 2018 International Conference on Supercomputing","location":"Beijing China","acronym":"ICS '18","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 2018 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205289.3205325","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3205289.3205325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:55Z","timestamp":1750208935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205289.3205325"}},"subtitle":["A Programming Framework for High Performance Text Analytics on Compressed Data"],"short-title":[],"issued":{"date-parts":[[2018,6,12]]},"references-count":35,"alternative-id":["10.1145\/3205289.3205325","10.1145\/3205289"],"URL":"https:\/\/doi.org\/10.1145\/3205289.3205325","relation":{},"subject":[],"published":{"date-parts":[[2018,6,12]]},"assertion":[{"value":"2018-06-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}