{"id":"https://openalex.org/W1981231959","doi":"https://doi.org/10.1145/2483969.2483972","title":"On collocations and topic models","display_name":"On collocations and topic models","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1981231959","doi":"https://doi.org/10.1145/2483969.2483972","mag":"1981231959"},"language":"en","primary_location":{"id":"doi:10.1145/2483969.2483972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2483969.2483972","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jey Han Lau","raw_affiliation_strings":["The University of Melbourne; NICTA Victoria Research Laboratory, Australia","The University of Melbourne"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne; NICTA Victoria Research Laboratory, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060332228","display_name":"Timothy Baldwin","orcid":"https://orcid.org/0000-0003-4525-6950"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Timothy Baldwin","raw_affiliation_strings":["The University of Melbourne; NICTA Victoria Research Laboratory, Australia","The University of Melbourne"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne; NICTA Victoria Research Laboratory, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088727983","display_name":"David Newman","orcid":"https://orcid.org/0000-0002-4959-2428"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Newman","raw_affiliation_strings":["University of California, Irvine"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032767467"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":9.8849,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.97823486,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":"3","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9937999844551086,"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/bigram","display_name":"Bigram","score":0.9884763956069946},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8988282084465027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8374662399291992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981345176696777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5353022217750549},{"id":"https://openalex.org/keywords/akaike-information-criterion","display_name":"Akaike information criterion","score":0.4246188998222351},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3846459984779358},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28027594089508057},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.2411257028579712}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9884763956069946},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8988282084465027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374662399291992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981345176696777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5353022217750549},{"id":"https://openalex.org/C126674687","wikidata":"https://www.wikidata.org/wiki/Q1662573","display_name":"Akaike information criterion","level":2,"score":0.4246188998222351},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3846459984779358},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28027594089508057},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.2411257028579712}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2483969.2483972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2483969.2483972","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.9298","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.9298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ww2.cs.mu.oz.au/~tim/pubs/tslp2013-topiccoll.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W25517462","https://openalex.org/W152260871","https://openalex.org/W170166889","https://openalex.org/W272752870","https://openalex.org/W658295343","https://openalex.org/W1529075208","https://openalex.org/W1574862351","https://openalex.org/W1604938182","https://openalex.org/W1880262756","https://openalex.org/W1897587124","https://openalex.org/W1974578407","https://openalex.org/W1984251878","https://openalex.org/W2033530841","https://openalex.org/W2042380438","https://openalex.org/W2042980227","https://openalex.org/W2096110600","https://openalex.org/W2096765155","https://openalex.org/W2097089247","https://openalex.org/W2104210067","https://openalex.org/W2126168798","https://openalex.org/W2130339025","https://openalex.org/W2142635246","https://openalex.org/W2147946282","https://openalex.org/W2149684865","https://openalex.org/W2159426623","https://openalex.org/W2163131995","https://openalex.org/W2168579166","https://openalex.org/W2169606435","https://openalex.org/W2524182563","https://openalex.org/W2606502803","https://openalex.org/W2606601345","https://openalex.org/W2607666848","https://openalex.org/W4205600580","https://openalex.org/W4255846079"],"related_works":["https://openalex.org/W2056250865","https://openalex.org/W1700330385","https://openalex.org/W2105076537","https://openalex.org/W2041167939","https://openalex.org/W2131111393","https://openalex.org/W2020757772","https://openalex.org/W2595298885","https://openalex.org/W2949624386","https://openalex.org/W2223833155","https://openalex.org/W198760020"],"abstract_inverted_index":{"We":[0,38,63,132],"investigate":[1],"the":[2,27,66,89,125,156,162,173,185],"impact":[3],"of":[4,85,127,164,188],"preextracting":[5],"and":[6,34,47,54,138,172],"tokenizing":[7],"bigram":[8,24],"collocations":[9,25],"on":[10,16,168],"topic":[11,36,91,102,110,170,181],"models.":[12],"Using":[13,94],"extensive":[14],"experiments":[15],"four":[17],"different":[18],"corpora,":[19],"we":[20],"show":[21,64,134],"that":[22,59,77,135,146],"incorporating":[23],"in":[26,43,100,109],"document":[28],"representation":[29],"creates":[30],"more":[31,72,129],"parsimonious":[32],"models":[33],"improves":[35],"coherence.":[37],"point":[39],"out":[40],"some":[41],"problems":[42],"interpreting":[44],"test":[45,48],"likelihood":[46],"perplexity":[49],"to":[50,83,118,159,176,180],"compare":[51],"model":[52,61],"fit,":[53],"suggest":[55],"an":[56],"alternate":[57],"measure":[58],"penalizes":[60],"complexity.":[62],"how":[65],"Akaike":[67],"information":[68],"criterion":[69],"is":[70,88,123,155],"a":[71,79,128],"appropriate":[73],"measure,":[74],"which":[75],"suggests":[76],"using":[78,116],"modest":[80],"number":[81],"(up":[82],"1000)":[84],"top-ranked":[86],"bigrams":[87,97],"optimal":[90],"modelling":[92,182],"configuration.":[93],"these":[95],"1000":[96],"also":[98,133],"results":[99],"improved":[101],"quality":[103,111],"over":[104],"unigram":[105],"tokenization.":[106,190],"Further":[107],"increases":[108],"can":[112],"be":[113,149],"achieved":[114],"by":[115],"up":[117],"10,000":[119],"bigrams,":[120],"but":[121],"this":[122],"at":[124],"cost":[126],"complex":[130],"model.":[131],"multiword":[136],"(bigram":[137],"longer)":[139],"named":[140],"entities":[141],"give":[142],"consistent":[143],"results,":[144],"indicating":[145],"they":[147],"should":[148],"represented":[150],"as":[151],"single":[152],"tokens.":[153],"This":[154],"first":[157,174],"work":[158,175],"explicitly":[160],"study":[161],"effect":[163],"n":[165],"-gram":[166],"tokenization":[167],"LDA":[169],"models,":[171],"make":[177],"empirical":[178],"recommendations":[179],"practitioners,":[183],"challenging":[184],"standard":[186],"practice":[187],"unigram-based":[189]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}