{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:05:40Z","timestamp":1729631140913,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/bigdata.2016.7840632","type":"proceedings-article","created":{"date-parts":[[2017,2,7]],"date-time":"2017-02-07T16:46:59Z","timestamp":1486486019000},"page":"416-423","source":"Crossref","is-referenced-by-count":2,"title":["HPTA: High-performance text analytics"],"prefix":"10.1109","author":[{"given":"Hans","family":"Vandierendonck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karen","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahwish","family":"Arif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitrios S.","family":"Nikolopoulos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Optimizing MapReduce for Multicore Architectures","year":"2010","author":"mao","key":"ref38"},{"article-title":"The Art of Computer Programming Volume 3: Sorting and Searching","year":"1998","author":"knuth","key":"ref33"},{"key":"ref32","article-title":"Region-based off-heap memory for Scala","author":"shabalin","year":"2015","journal-title":"EPFL Tech Rep"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/512529.512563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.17487\/rfc3629"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/277650.277725"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1996092.1996095"},{"year":"2016","key":"ref34","article-title":"NSF research awards abstracts 1990–2003"},{"key":"ref10","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"ref12","first-page":"15","article-title":"API design for machine learning software: experiences from the scikit-learn project","author":"buitinck","year":"2013","journal-title":"ECML\/PKDD Workshop on Languages for Data Mining and Machine Learning"},{"key":"ref13","first-page":"45","article-title":"Software framework for topic modelling with large corpora","author":"rehurek","year":"2010","journal-title":"Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2006.50"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.08.062"},{"key":"ref16","first-page":"1","article-title":"Large-scale multidimensional document clustering on GPU clusters","author":"zhang","year":"2010","journal-title":"Parallel Distributed Processing (IPDPS) 2010 IEEE Intl Symp"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2010.08.002"},{"article-title":"Document stream clustering using GPUs","year":"2013","author":"szaszy","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1007\/3-540-49530-4_32","article-title":"Standard templates adaptive parallel library (STAPL)","author":"rauchwerger","year":"1998","journal-title":"LCR '98 Selected Papers from the 4th Intl Workshop on Languages Compilers and Run-Time Systems for Scalable Computers"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2754169.2754185"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"journal-title":"Prefix Sums and Their Applications","year":"1990","author":"blelloch","key":"ref27"},{"key":"ref3","first-page":"293","article-title":"Making sense of performance in data analytics frameworks","author":"ousterhout","year":"2015","journal-title":"Proc of the 8th USENIX Conf on Networked Systems Design and Implementation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610518"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/378795.378815"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14778\/2732977.2732980"},{"year":"2016","key":"ref8","article-title":"Apache spark"},{"year":"2016","key":"ref7","article-title":"Apache hadoop"},{"key":"ref2","article-title":"Scalability! but at what COST?","author":"mcsherry","year":"2015","journal-title":"15th Workshop on Hot Topics in Operating Systems (HotOS XV)"},{"key":"ref9","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc of the 8th USENIX Conf on Networked Systems Design and Implementation"},{"article-title":"Unstructured data and the 80 percent rule","year":"2008","author":"grimes","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85261-2_11"},{"journal-title":"PDQCollections A data-parallel programming model and library for associative containers ”","year":"2013","author":"varshney","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263614"},{"year":"2014","key":"ref24","article-title":"International standard ISO\/IEC 14882:2014(E) programming language C++"},{"journal-title":"Introduction to Modern Information Retrieval","year":"1983","author":"salton","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346181"},{"key":"ref25","article-title":"The Art of Computer Programming","volume":"1","author":"knuth","year":"1997","journal-title":"Fundamental Algorithms"}],"event":{"name":"2016 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2016,12,5]]},"location":"Washington DC,USA","end":{"date-parts":[[2016,12,8]]}},"container-title":["2016 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7818133\/7840573\/07840632.pdf?arnumber=7840632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T07:18:29Z","timestamp":1568791109000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7840632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2016.7840632","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}