{"id":"https://openalex.org/W2250988012","doi":"https://doi.org/10.18653/v1/d15-1288","title":"Compact, Efficient and Unlimited Capacity: Language Modeling with Compressed Suffix Trees","display_name":"Compact, Efficient and Unlimited Capacity: Language Modeling with Compressed Suffix Trees","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250988012","doi":"https://doi.org/10.18653/v1/d15-1288","mag":"2250988012"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1288","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1288","pdf_url":"https://www.aclweb.org/anthology/D15-1288.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1288.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086032589","display_name":"Ehsan Shareghi","orcid":null},"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"]},{"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 Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595","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"]},{"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":"Matthias Petri","raw_affiliation_strings":["Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I56590836"]}]},{"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/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"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 Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595","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"]},{"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":"Trevor Cohn","raw_affiliation_strings":["Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University Computing and Information Systems, The University of Melbourne","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5614,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9380424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2409","last_page":"2418"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9987999796867371,"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":0.8566913604736328},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.8040934801101685},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.7847779989242554},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.688392698764801},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5893069505691528},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5811296701431274},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5433180928230286},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.502305269241333},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43619561195373535},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.42661598324775696},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.4179793894290924},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39539268612861633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31618139147758484},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.290407657623291},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1338936984539032},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12666592001914978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09859326481819153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566913604736328},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.8040934801101685},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.7847779989242554},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.688392698764801},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5893069505691528},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5811296701431274},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5433180928230286},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.502305269241333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43619561195373535},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.42661598324775696},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.4179793894290924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39539268612861633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31618139147758484},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.290407657623291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1338936984539032},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12666592001914978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09859326481819153},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d15-1288","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1288","pdf_url":"https://www.aclweb.org/anthology/D15-1288.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.6794","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.6794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1288.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.713.7978","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.713.7978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.monash.edu.au/%7Egholamrh/publications/cstlm-emnlp15.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1288","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1288","pdf_url":"https://www.aclweb.org/anthology/D15-1288.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310369","display_name":"National ICT Australia","ror":"https://ror.org/03q397159"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250988012.pdf","grobid_xml":"https://content.openalex.org/works/W2250988012.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W126222424","https://openalex.org/W1549037892","https://openalex.org/W1560013842","https://openalex.org/W1631260214","https://openalex.org/W1916559533","https://openalex.org/W1934041838","https://openalex.org/W1962019683","https://openalex.org/W2030962049","https://openalex.org/W2041445031","https://openalex.org/W2057147815","https://openalex.org/W2059513841","https://openalex.org/W2067974452","https://openalex.org/W2069074882","https://openalex.org/W2073921136","https://openalex.org/W2097927681","https://openalex.org/W2106540279","https://openalex.org/W2107082304","https://openalex.org/W2109664771","https://openalex.org/W2122429665","https://openalex.org/W2128808215","https://openalex.org/W2134800885","https://openalex.org/W2135208303","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2171913306","https://openalex.org/W2172097231","https://openalex.org/W2250193734","https://openalex.org/W2295986819","https://openalex.org/W2533248932","https://openalex.org/W2950186769","https://openalex.org/W2952380754","https://openalex.org/W3211848854"],"related_works":["https://openalex.org/W96331545","https://openalex.org/W2003608043","https://openalex.org/W1517600056","https://openalex.org/W2405892617","https://openalex.org/W2073921136","https://openalex.org/W4293529780","https://openalex.org/W1575722140","https://openalex.org/W3022556214","https://openalex.org/W2160738675","https://openalex.org/W1548907175"],"abstract_inverted_index":{"Efficient":[0],"methods":[1,24],"for":[2,10,25,60],"storing":[3],"and":[4,15,74],"querying":[5],"language":[6,68],"models":[7],"are":[8],"critical":[9],"scaling":[11,84],"to":[12],"large":[13,28],"corpora":[14,29],"high":[16],"Markov":[17,33],"orders.":[18],"In":[19],"this":[20],"paper":[21],"we":[22,87],"propose":[23],"modeling":[26,91],"extremely":[27],"without":[30],"imposing":[31],"a":[32,41,66],"condition.":[34],"At":[35],"its":[36],"core,":[37],"our":[38],"approach":[39],"uses":[40],"succinct":[42],"index":[43],"-a":[44],"compressed":[45],"suffix":[46],"tree":[47],"-which":[48],"provides":[49],"near":[50],"optimal":[51],"compression":[52],"while":[53],"supporting":[54],"efficient":[55],"search.":[56],"We":[57],"present":[58],"algorithms":[59],"on-the-fly":[61],"computation":[62],"of":[63],"probabilities":[64],"under":[65],"Kneser-Ney":[67],"model.":[69],"Our":[70],"technique":[71],"is":[72],"exact":[73],"although":[75],"slower":[76],"than":[77],"leading":[78],"LM":[79],"toolkits,":[80],"it":[81],"shows":[82],"promising":[83],"properties,":[85],"which":[86],"demonstrate":[88],"through":[89],"-order":[90],"over":[92],"the":[93],"full":[94],"Wikipedia":[95],"collection.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}