{"id":"https://openalex.org/W7137920034","doi":"https://doi.org/10.1609/aaai.v40i17.38482","title":"Intermediate N-Gramming: Deterministic and Fast N-Grams for Large N and Large Datasets","display_name":"Intermediate N-Gramming: Deterministic and Fast N-Grams for Large N and Large Datasets","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137920034","doi":"https://doi.org/10.1609/aaai.v40i17.38482"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i17.38482","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38482","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38482/42444","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38482/42444","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026833192","display_name":"Ryan R. Curtin","orcid":"https://orcid.org/0000-0002-9903-8214"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan R. Curtin","raw_affiliation_strings":["Booz Allen Hamilton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129688134","display_name":"Fred Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Lu","raw_affiliation_strings":["University of Maryland, Baltimore County"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["CrowdStrike\nUniversity of Maryland, Baltimore County"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CrowdStrike\nUniversity of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090051188","display_name":"Priyanka Ranade","orcid":"https://orcid.org/0000-0003-3859-5356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Ranade","raw_affiliation_strings":["Laboratory for Physical Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13105413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"17","first_page":"14639","last_page":"14647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.4675999879837036,"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":0.4675999879837036,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.11320000141859055,"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/T11567","display_name":"semigroups and automata theory","score":0.0494999997317791,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/speedup","display_name":"Speedup","score":0.6988000273704529},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4401000142097473},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.3856000006198883},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.36559998989105225},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.36419999599456787},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.35359999537467957}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845999956130981},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C98385598","wikidata":"https://www.wikidata.org/wiki/Q1339385","display_name":"Empirical distribution function","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i17.38482","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38482","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38482/42444","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38482","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i17.38482","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38482","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38482/42444","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5619493722915649,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137920034.pdf","grobid_xml":"https://content.openalex.org/works/W7137920034.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"number":[1],"of":[2,83,120],"n-gram":[3,35],"features":[4],"grows":[5],"exponentially":[6],"in":[7,74],"n,":[8],"making":[9],"it":[10,40],"computationally":[11],"demanding":[12],"to":[13,42,87,101,116],"compute":[14],"the":[15,48,65,90,102,106,118],"most":[16,50],"frequent":[17,51],"n-grams":[18,63],"even":[19,95],"for":[20],"n":[21],"as":[22,24],"small":[23],"3.":[25],"Motivated":[26],"by":[27],"our":[28,76,121],"production":[29],"machine":[30],"learning":[31],"system":[32],"built":[33],"on":[34],"features,":[36],"we":[37,112],"ask:":[38],"is":[39],"possible":[41],"accurately,":[43],"deterministically,":[44],"and":[45],"quickly":[46],"recover":[47],"top-k":[49],"n-grams?":[52],"We":[53],"devise":[54],"a":[55],"multi-pass":[56,122],"algorithm":[57,71],"called":[58],"Intergrams":[59],"that":[60],"constructs":[61],"candidate":[62],"from":[64],"preceding":[66],"(n-1)-grams.":[67],"By":[68],"designing":[69],"this":[70],"with":[72],"hardware":[73],"mind,":[75],"approach":[77],"yields":[78],"more":[79],"than":[80],"an":[81],"order":[82],"magnitude":[84],"speedup":[85],"(up":[86],"33x!)":[88],"over":[89,110],"next":[91],"known":[92],"fastest":[93],"algorithm,":[94],"when":[96],"similar":[97],"optimization":[98],"are":[99],"applied":[100],"other":[103],"algorithm.":[104],"Using":[105],"empirical":[107],"power-law":[108],"distribution":[109],"n-grams,":[111],"also":[113],"provide":[114],"theory":[115],"inform":[117],"efficacy":[119],"approach.":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
