{"id":"https://openalex.org/W2740353565","doi":"https://doi.org/10.1145/3077136.3080798","title":"Efficient Data Structures for MassiveN-Gram Datasets","display_name":"Efficient Data Structures for MassiveN-Gram Datasets","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740353565","doi":"https://doi.org/10.1145/3077136.3080798","mag":"2740353565"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3080798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10278/5023384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010860687","display_name":"Giulio Ermanno Pibiri","orcid":"https://orcid.org/0000-0003-0724-7092"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulio Ermanno Pibiri","raw_affiliation_strings":["University of Pisa & ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa & ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I108290504","https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084138015","display_name":"Rossano Venturini","orcid":"https://orcid.org/0000-0002-9830-3936"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rossano Venturini","raw_affiliation_strings":["University of Pisa & ISTI-CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa & ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I108290504","https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.694,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.74317867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"615","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","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/T11269","display_name":"Algorithms and Data Compression","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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12029","display_name":"DNA and Biological Computing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8626446723937988},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8481662273406982},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.8297543525695801},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5460893511772156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44752633571624756},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.43093836307525635},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41933003067970276},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4137674570083618},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41013044118881226},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.16796207427978516},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16213759779930115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626446723937988},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8481662273406982},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.8297543525695801},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5460893511772156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44752633571624756},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.43093836307525635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41933003067970276},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4137674570083618},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41013044118881226},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.16796207427978516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16213759779930115},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3077136.3080798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/887214","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/887214","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dnet:people______::1864b4c0466cbb15e38e30ce0d5cf3dd","is_oa":false,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::1864b4c0466cbb15e38e30ce0d5cf3dd","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 615\u2013624, Tokyo, Giappone, 7-11/08/2017","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:iris.unive.it:10278/5023384","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5023384","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:zenodo.org:3503737","is_oa":true,"landing_page_url":"https://zenodo.org/record/3503737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:iris.unive.it:10278/5023384","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5023384","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4365905886","display_name":null,"funder_award_id":"-2014-2015","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G495187929","display_name":null,"funder_award_id":"EU\u2010H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5848184290","display_name":null,"funder_award_id":"654024","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W84899576","https://openalex.org/W182831726","https://openalex.org/W1509727978","https://openalex.org/W1535755777","https://openalex.org/W1559631118","https://openalex.org/W1978294273","https://openalex.org/W1987007212","https://openalex.org/W1989234058","https://openalex.org/W2010595692","https://openalex.org/W2031302834","https://openalex.org/W2057223122","https://openalex.org/W2060575618","https://openalex.org/W2063163001","https://openalex.org/W2071001390","https://openalex.org/W2076489648","https://openalex.org/W2087426910","https://openalex.org/W2089455813","https://openalex.org/W2099926694","https://openalex.org/W2103803302","https://openalex.org/W2123845384","https://openalex.org/W2128808215","https://openalex.org/W2134800885","https://openalex.org/W2148578434","https://openalex.org/W2149243190","https://openalex.org/W2155512447","https://openalex.org/W2164986850","https://openalex.org/W2171913306","https://openalex.org/W2337480916","https://openalex.org/W2611669587","https://openalex.org/W4246820370"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W4247016990","https://openalex.org/W2084276039","https://openalex.org/W2073246449","https://openalex.org/W2789473152"],"abstract_inverted_index":{"The":[0],"efficient":[1],"indexing":[2],"of":[3,24,32,37],"large":[4],"and":[5,20],"sparse":[6],"N-gram":[7],"datasets":[8],"is":[9],"crucial":[10],"in":[11,14],"several":[12],"applications":[13],"Information":[15],"Retrieval,":[16],"Natural":[17],"Language":[18],"Processing":[19],"Machine":[21],"Learning.":[22],"Because":[23],"the":[25,35,44],"stringent":[26],"efficiency":[27],"requirements,":[28],"dealing":[29],"with":[30],"billions":[31],"N-grams":[33],"poses":[34],"challenge":[36],"introducing":[38],"a":[39],"compressed":[40],"representation":[41],"that":[42],"preserves":[43],"query":[45],"processing":[46],"speed.":[47]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2017-08-08T00:00:00"}