{"id":"https://openalex.org/W2612140416","doi":"https://doi.org/10.1017/s1351324917000092","title":"A scalable architecture for data-intensive natural language processing","display_name":"A scalable architecture for data-intensive natural language processing","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2612140416","doi":"https://doi.org/10.1017/s1351324917000092","mag":"2612140416"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324917000092","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324917000092","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028196038","display_name":"Zuhaitz Beloki","orcid":"https://orcid.org/0000-0003-0469-5076"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"ZUHAITZ BELOKI","raw_affiliation_strings":["IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","University of the Basque Country (UPV/EHU)"],"raw_orcid":"https://orcid.org/0000-0003-0469-5076","affiliations":[{"raw_affiliation_string":"IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019879095","display_name":"Xabier Artola Zubillaga","orcid":"https://orcid.org/0000-0003-1921-2436"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"XABIER ARTOLA","raw_affiliation_strings":["IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","University of the Basque Country (UPV/EHU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053230169","display_name":"Aitor Soroa","orcid":"https://orcid.org/0000-0001-8573-2654"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"AITOR SOROA","raw_affiliation_strings":["IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","University of the Basque Country (UPV/EHU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IXA NLP Group, University of the Basque Country (UPV/EHU), Donostia-San Sebasti\u00e1n e-mail:","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"University of the Basque Country (UPV/EHU)","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":0.3988,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69845208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":"5","first_page":"709","last_page":"731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9232320785522461},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7413032650947571},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7238674163818359},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6218159198760986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115969777107239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4586089253425598},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37180328369140625},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2153576910495758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9232320785522461},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7413032650947571},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7238674163818359},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6218159198760986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115969777107239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4586089253425598},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37180328369140625},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2153576910495758},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324917000092","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324917000092","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W11336434","https://openalex.org/W1494834878","https://openalex.org/W1560505539","https://openalex.org/W1607983314","https://openalex.org/W1663984431","https://openalex.org/W1798501848","https://openalex.org/W1870868768","https://openalex.org/W2007848212","https://openalex.org/W2173213060","https://openalex.org/W2180034260","https://openalex.org/W2251951031","https://openalex.org/W2396200542","https://openalex.org/W2415378597","https://openalex.org/W2528705463","https://openalex.org/W2734546602","https://openalex.org/W4391418904","https://openalex.org/W6600464600","https://openalex.org/W6691775334","https://openalex.org/W6740829226"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W4384345686","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W2145834781","https://openalex.org/W2577782152","https://openalex.org/W262455470","https://openalex.org/W4242899858","https://openalex.org/W2356327704","https://openalex.org/W4240746485"],"abstract_inverted_index":{"Abstract":[0],"Computational":[1],"power":[2],"needs":[3,41],"have":[4,42],"greatly":[5],"increased":[6],"during":[7],"the":[8,15,18,48,87,111,146,159,178,223,228,239,251,254,258,263],"last":[9],"years,":[10],"and":[11,51,105,168,191,213,222,233],"this":[12,60],"is":[13,116],"also":[14,242],"case":[16],"in":[17,34,47,57,103,150,227,250,266],"Natural":[19],"Language":[20],"Processing":[21],"(NLP)":[22],"area,":[23],"where":[24],"thousands":[25],"of":[26,90,122,142,163,180,218,246,253,260],"documents":[27],"must":[28],"be":[29,133,209],"processed,":[30],"i.e.,":[31,139],"linguistically":[32],"analyzed,":[33],"a":[35,44,64,81,120,127,136,140,156,173,203,216,244],"reasonable":[36],"time":[37],"frame.":[38],"These":[39],"computing":[40,49],"implied":[43],"radical":[45],"change":[46],"architectures":[50],"big-scale":[52],"text":[53],"processing":[54,82,129,187],"techniques":[55],"used":[56,226],"NLP.":[58],"In":[59,238],"paper,":[61,240],"we":[62,194,241],"present":[63],"scalable":[65],"architecture":[66,72,112,206],"for":[67,189],"distributed":[68,101,137,205,234],"language":[69],"processing.":[70],"The":[71,220],"uses":[73],"Storm":[74],"to":[75,99,118,166],"combine":[76],"diverse":[77],"NLP":[78,124,160,224],"modules":[79,125,148,161,225],"into":[80,126],"chain,":[83],"which":[84,131],"carries":[85],"out":[86,249],"linguistic":[88,170,186],"analysis":[89],"documents.":[91],"Scalability":[92],"requires":[93],"designing":[94],"solutions":[95],"that":[96,198,207],"are":[97,154,230],"able":[98,165],"run":[100,149],"programs":[102],"parallel":[104],"across":[106],"large":[107],"machine":[108],"clusters.":[109],"Using":[110],"presented":[113],"here,":[114],"it":[115],"possible":[117],"integrate":[119],"set":[121],"third-party":[123],"unique":[128],"chain":[130],"can":[132,208],"deployed":[134,214],"onto":[135,215],"environment,":[138],"cluster":[141,217],"machines,":[143],"so":[144],"allowing":[145],"language-processing":[147],"parallel.":[151],"No":[152],"restrictions":[153],"placed":[155],"priori":[157],"on":[158],"apart":[162],"being":[164],"consume":[167],"produce":[169],"annotations":[171],"following":[172],"given":[174],"format.":[175],"We":[176],"show":[177],"feasibility":[179],"our":[181],"approach":[182],"by":[183],"integrating":[184],"two":[185],"chains":[188],"English":[190],"Spanish.":[192],"Moreover,":[193],"provide":[195],"several":[196],"scripts":[197,221],"allow":[199],"building":[200],"from":[201],"scratch":[202],"whole":[204],"then":[210],"easily":[211],"installed":[212],"machines.":[219],"paper":[229],"publicly":[231],"available":[232],"under":[235],"free":[236],"licenses.":[237],"describe":[243],"series":[245],"experiments":[247],"carried":[248],"context":[252],"NewsReader":[255],"project":[256],"with":[257],"goal":[259],"testing":[261],"how":[262],"system":[264],"behaves":[265],"different":[267],"scenarios.":[268]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
