{"id":"https://openalex.org/W2511632062","doi":"https://doi.org/10.1162/tacl_a_00112","title":"Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees","display_name":"Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2511632062","doi":"https://doi.org/10.1162/tacl_a_00112","mag":"2511632062"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00112","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00112","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00112","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086032589","display_name":"Ehsan Shareghi","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ehsan Shareghi","raw_affiliation_strings":["Faculty of Information Technology, Monash University,","Faculty of Information Technology, Monash University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University,","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Faculty of Information Technology, Monash University#TAB#","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980890","display_name":"Matthias Petri","orcid":"https://orcid.org/0000-0002-0054-9429"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Matthias Petri","raw_affiliation_strings":["Computing and Information Systems, The University of Melbourne,","Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing and Information Systems, The University of Melbourne,","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gholamreza Haffari","raw_affiliation_strings":["Faculty of Information Technology, Monash University,","Faculty of Information Technology, Monash University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University,","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Faculty of Information Technology, Monash University#TAB#","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":["Computing and Information Systems, The University of Melbourne,","Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing and Information Systems, The University of Melbourne,","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.04784378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"477","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9995999932289124,"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":0.879116415977478},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.786253809928894},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5165637731552124},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.443963885307312},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4410002827644348},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.4339381456375122},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43130791187286377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3849884867668152},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37271279096603394},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.34074974060058594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3312452435493469},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11489656567573547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.879116415977478},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.786253809928894},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5165637731552124},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.443963885307312},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4410002827644348},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4339381456375122},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43130791187286377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849884867668152},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37271279096603394},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.34074974060058594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3312452435493469},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11489656567573547},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1162/tacl_a_00112","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00112","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00112","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1608.04465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.04465","pdf_url":"https://arxiv.org/pdf/1608.04465","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2511632062","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1608.04465.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:4c8bc92828e146d1bacacf78de28f758","is_oa":false,"landing_page_url":"https://doaj.org/article/4c8bc92828e146d1bacacf78de28f758","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Transactions of the Association for Computational Linguistics, Vol 4 (2021)","raw_type":"article"},{"id":"pmh:oai:monash.edu:publications/48d3deb5-22f1-4b58-a91c-0f06a78698f8","is_oa":true,"landing_page_url":"https://www.transacl.org/ojs/index.php/tacl/article/view/865/211","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"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":"Shareghi, E, Petri, M, Haffari, G & Cohn, T 2016, 'Fast, small and exact : infinite-order language modelling with compressed suffix trees', Transactions of the Association for Computational Linguistics, vol. 4, pp. 477-490. < https://www.transacl.org/ojs/index.php/tacl/article/view/865/211 >","raw_type":"article"},{"id":"doi:10.48550/arxiv.1608.04465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.04465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00112","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00112","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00112","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5826793460","display_name":"Adaptive Context-Dependent Machine Translation for Heterogeneous Text","funder_award_id":"FT130101105","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320310369","display_name":"National ICT Australia","ror":"https://ror.org/03q397159"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2511632062.pdf","grobid_xml":"https://content.openalex.org/works/W2511632062.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W87260881","https://openalex.org/W126222424","https://openalex.org/W1549037892","https://openalex.org/W1551461028","https://openalex.org/W1985174631","https://openalex.org/W2057147815","https://openalex.org/W2086536051","https://openalex.org/W2106540279","https://openalex.org/W2109664771","https://openalex.org/W2158195707","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2171913306","https://openalex.org/W2189576523","https://openalex.org/W2250653840","https://openalex.org/W2250988012","https://openalex.org/W2295986819","https://openalex.org/W2533248932","https://openalex.org/W2951714314"],"related_works":["https://openalex.org/W2963766645","https://openalex.org/W2984997202","https://openalex.org/W2089545095","https://openalex.org/W2732093072","https://openalex.org/W2077333702","https://openalex.org/W2400487982","https://openalex.org/W1548111976","https://openalex.org/W2100352580","https://openalex.org/W2020258599","https://openalex.org/W2167406488","https://openalex.org/W2343984634","https://openalex.org/W2108706843","https://openalex.org/W2949094631","https://openalex.org/W1980160594","https://openalex.org/W3086212533","https://openalex.org/W1986324942","https://openalex.org/W1877511701","https://openalex.org/W1554611468","https://openalex.org/W192080074","https://openalex.org/W1986880831"],"abstract_inverted_index":{"Efficient":[0],"methods":[1],"for":[2,8],"storing":[3],"and":[4,33,70,76,101],"querying":[5],"are":[6,105],"critical":[7],"scaling":[9],"high-order":[10],"m-gram":[11],"language":[12,20,46],"models":[13],"to":[14,59],"large":[15,74],"corpora.":[16],"We":[17,50],"propose":[18],"a":[19,27,64],"model":[21,47],"based":[22],"on":[23],"compressed":[24],"suffix":[25],"trees,":[26],"representation":[28],"that":[29,104],"is":[30,82],"highly":[31,83],"compact":[32],"can":[34],"be":[35],"easily":[36],"held":[37],"in":[38,44,67],"memory,":[39],"while":[40],"supporting":[41],"queries":[42],"needed":[43],"computing":[45],"probabilities":[48],"on-the-fly.":[49],"present":[51],"several":[52],"optimisations":[53],"which":[54],"improve":[55],"query":[56],"runtimes":[57,103],"up":[58],"2500\u00d7,":[60],"despite":[61],"only":[62],"incurring":[63],"modest":[65],"increase":[66],"construction":[68],"time":[69],"memory":[71,94],"usage.":[72],"For":[73],"corpora":[75],"high":[77],"Markov":[78],"orders,":[79],"our":[80],"method":[81],"competitive":[84],"with":[85],"the":[86],"state-of-the-art":[87],"KenLM":[88],"package.":[89],"It":[90],"imposes":[91],"much":[92],"lower":[93],"requirements,":[95],"often":[96],"by":[97],"orders":[98],"of":[99],"magnitude,":[100],"has":[102],"either":[106],"similar":[107],"(for":[108,112],"training)":[109],"or":[110],"comparable":[111],"querying).":[113]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}