{"id":"https://openalex.org/W2105686649","doi":"https://doi.org/10.1613/jair.374","title":"Identifying Hierarchical Structure in Sequences: A linear-time algorithm","display_name":"Identifying Hierarchical Structure in Sequences: A linear-time algorithm","publication_year":1997,"publication_date":"1997-09-01","ids":{"openalex":"https://openalex.org/W2105686649","doi":"https://doi.org/10.1613/jair.374","mag":"2105686649"},"language":"en","primary_location":{"id":"doi:10.1613/jair.374","doi":"https://doi.org/10.1613/jair.374","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.374","pdf_url":"https://jair.org/index.php/jair/article/download/10192/24208","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/10192/24208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087827173","display_name":"Craig G. Nevill-Manning","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"C. G. Nevill-Manning","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045934263","display_name":"Ian H. Witten","orcid":"https://orcid.org/0000-0001-6428-8988","observed_orcids":["https://orcid.org/0000-0001-6428-8988"]},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"I. H. Witten","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New zealand","institution_ids":["https://openalex.org/I52179390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52179390"],"apc_list":null,"apc_paid":null,"fwci":7.4074,"has_fulltext":true,"cited_by_count":581,"citation_normalized_percentile":{"value":0.98218263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"67","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9355000257492065,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9355000257492065,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11567","display_name":"semigroups and automata theory","score":0.061000000685453415,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0017999999690800905,"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/hierarchy","display_name":"hierarchy","score":0.5830000042915344},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"sequence analysis","score":0.5189999938011169},{"id":"https://openalex.org/keywords/grammatical-inference","display_name":"grammatical inference","score":0.5849999785423279},{"id":"https://openalex.org/keywords/linear-time-algorithms","display_name":"linear-time algorithms","score":0.7730000019073486},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"incremental learning","score":0.5559999942779541},{"id":"https://openalex.org/keywords/lexical-structure","display_name":"lexical structure","score":0.640999972820282},{"id":"https://openalex.org/keywords/grammar-compression","display_name":"grammar compression","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6756314635276794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.634918749332428},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6076829433441162},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5807303190231323},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5113286375999451},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5027930736541748},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5012390613555908},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4413371980190277},{"id":"https://openalex.org/C80877019","wikidata":"https://www.wikidata.org/wiki/Q7188074","display_name":"Phrase structure rules","level":3,"score":0.4251849353313446},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.41741156578063965},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37237948179244995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30801865458488464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08489587903022766},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.1613/jair.374","doi":"https://doi.org/10.1613/jair.374","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.374","pdf_url":"https://jair.org/index.php/jair/article/download/10192/24208","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:cs/9709102","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cs/9709102","pdf_url":"https://arxiv.org/pdf/cs/9709102","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,"listed_in":[],"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":"pmh:oai:CiteSeerX.psu:10.1.1.170.2233","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.2233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hum.uchicago.edu/%7Ejagoldsm/CompLing/NevillManning_Witten_1997.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.8942","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.8942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.waikato.ac.nz/~ihw/papers/97NM-IHW-Ident-Hier.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.342.2769","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.342.2769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/cs/9709102v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.3846","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.3846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.washington.edu/research/jair/volume7/nevill97a.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.7866","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.7866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jair.org/media/374/live-374-1630-jair.pdf","raw_type":"text"},{"id":"pmh:oai:researchcommons.waikato.ac.nz:10289/1186","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10289/1186","pdf_url":null,"source":{"id":"https://openalex.org/S7407063277","display_name":"Research Commons (University of Waikato)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"Working Paper"},{"id":"doi:10.48550/arxiv.cs/9709102","doi":"https://doi.org/10.48550/arxiv.cs/9709102","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.cs/9709102","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:3003570873","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1622776.1622780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":null}],"best_oa_location":{"id":"doi:10.1613/jair.374","doi":"https://doi.org/10.1613/jair.374","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.374","pdf_url":"https://jair.org/index.php/jair/article/download/10192/24208","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2105686649.pdf","grobid_xml":"https://content.openalex.org/works/W2105686649.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W591184081","https://openalex.org/W600912821","https://openalex.org/W1492324553","https://openalex.org/W1552948490","https://openalex.org/W1575798196","https://openalex.org/W1969005071","https://openalex.org/W1993449345","https://openalex.org/W2015047612","https://openalex.org/W2033180506","https://openalex.org/W2056933273","https://openalex.org/W2059504991","https://openalex.org/W2075924004","https://openalex.org/W2091903496","https://openalex.org/W2092386826","https://openalex.org/W2105594594","https://openalex.org/W2109893852","https://openalex.org/W2112803765","https://openalex.org/W2127257326","https://openalex.org/W2129572684","https://openalex.org/W2135208096","https://openalex.org/W2166274056","https://openalex.org/W2187526581","https://openalex.org/W2611071497"],"related_works":["https://openalex.org/W3003570873","https://openalex.org/W2059504991","https://openalex.org/W99885242","https://openalex.org/W2107333654","https://openalex.org/W1836657414","https://openalex.org/W1480780803","https://openalex.org/W3091169818","https://openalex.org/W7100983617","https://openalex.org/W7095724768","https://openalex.org/W2138947530"],"abstract_inverted_index":{"SEQUITUR":[0,69],"is":[1,34,51,92],"an":[2,113],"algorithm":[3,50],"that":[4,23,56,84,91],"infers":[5],"a":[6,10,20,35,67,82],"hierarchical":[7,36],"structure":[8,65,80],"from":[9],"sequence":[11],"of":[12,38,60,97,116],"discrete":[13],"symbols":[14,105],"by":[15,53,73],"replacing":[16],"repeated":[17],"phrases":[18],"with":[19],"grammatical":[21],"rule":[22],"generates":[24],"the":[25,39,58,61,77,95,98],"phrase,":[26],"and":[27,63,89,108],"continuing":[28],"this":[29],"process":[30,103],"recursively.":[31],"The":[32,49],"result":[33],"representation":[37],"original":[40],"sequence,":[41],"which":[42],"offers":[43],"insights":[44],"into":[45],"its":[46],"lexical":[47],"structure.":[48],"driven":[52],"two":[54],"constraints":[55],"reduce":[57],"size":[59,96],"grammar,":[62],"produce":[64],"as":[66],"by-product.":[68],"breaks":[70],"new":[71],"ground":[72],"operating":[74],"incrementally.":[75],"Moreover,":[76],"method's":[78],"simple":[79],"permits":[81],"proof":[83],"it":[85],"operates":[86],"in":[87,94],"space":[88],"time":[90],"linear":[93],"input.":[99],"Our":[100],"implementation":[101],"can":[102],"50,000":[104],"per":[106],"second":[107],"has":[109],"been":[110],"applied":[111],"to":[112],"extensive":[114],"range":[115],"real":[117],"world":[118],"sequences.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":37},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":17}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}