{"id":"https://openalex.org/W2950494126","doi":"https://doi.org/10.18653/v1/p19-1396","title":"Leveraging Meta Information in Short Text Aggregation","display_name":"Leveraging Meta Information in Short Text Aggregation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950494126","doi":"https://doi.org/10.18653/v1/p19-1396","mag":"2950494126"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1396","pdf_url":"https://www.aclweb.org/anthology/P19-1396.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1396.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038625195","display_name":"He Zhao","orcid":"https://orcid.org/0000-0002-8264-9297"},"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":true,"raw_author_name":"He Zhao","raw_affiliation_strings":["Faculty of Information Technology Monash University, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021845515","display_name":"Lan Du","orcid":"https://orcid.org/0000-0002-9925-0223"},"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":"Lan Du","raw_affiliation_strings":["Faculty of Information Technology Monash University, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070515519","display_name":"Guanfeng Liu","orcid":"https://orcid.org/0000-0001-8980-4950"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guanfeng Liu","raw_affiliation_strings":["Department of Computing Macquarie University, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005792924","display_name":"Wray Buntine","orcid":"https://orcid.org/0000-0001-9292-1015"},"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":"Wray Buntine","raw_affiliation_strings":["Faculty of Information Technology Monash University, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038625195"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":0.2886,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65745751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4042","last_page":"4049"},"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":0.9991000294685364,"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":0.9973000288009644,"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":0.7945123314857483},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6304829716682434},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5758749842643738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689783692359924},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.519536554813385},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5168645977973938},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4948365092277527},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4939137101173401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47728267312049866},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.47470369935035706},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.42862948775291443},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4206909239292145},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3621973395347595},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12220558524131775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08588990569114685},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08050784468650818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945123314857483},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6304829716682434},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5758749842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689783692359924},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.519536554813385},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5168645977973938},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4948365092277527},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4939137101173401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47728267312049866},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.47470369935035706},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.42862948775291443},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4206909239292145},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3621973395347595},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12220558524131775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08588990569114685},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08050784468650818},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1396","pdf_url":"https://www.aclweb.org/anthology/P19-1396.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:monash.edu:publications/ffb776d9-c587-401a-bd06-f411bd184891","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/ffb776d9-c587-401a-bd06-f411bd184891","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":"Zhao , H , Du , L , Liu , G & Buntine , W 2019 , Leveraging meta information in short text aggregation . in A Korhonen , D Traum & L M\u00e0rquez (eds) , Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics (ACL) , Florence Italy , pp. 4042-4049 , Annual Meeting of the Association of Computational Linguistics 2019 , Florence , Italy , 28/07/19 . https://doi.org/10.18653/v1/P19-1396","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1396","pdf_url":"https://www.aclweb.org/anthology/P19-1396.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950494126.pdf","grobid_xml":"https://content.openalex.org/works/W2950494126.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1714665356","https://openalex.org/W1880262756","https://openalex.org/W2004192095","https://openalex.org/W2063904635","https://openalex.org/W2085534751","https://openalex.org/W2115529864","https://openalex.org/W2151703435","https://openalex.org/W2168332560","https://openalex.org/W2178725228","https://openalex.org/W2222893162","https://openalex.org/W2238728730","https://openalex.org/W2250239827","https://openalex.org/W2250533720","https://openalex.org/W2250539671","https://openalex.org/W2250753706","https://openalex.org/W2251410829","https://openalex.org/W2251582277","https://openalex.org/W2293543073","https://openalex.org/W2340381866","https://openalex.org/W2516537890","https://openalex.org/W2577167923","https://openalex.org/W2585828887","https://openalex.org/W2642282775","https://openalex.org/W2745475103","https://openalex.org/W2755330151","https://openalex.org/W2788615138","https://openalex.org/W2790504398","https://openalex.org/W2798994835","https://openalex.org/W2800340640","https://openalex.org/W2804385163","https://openalex.org/W2804429990","https://openalex.org/W2899112946","https://openalex.org/W2962943175","https://openalex.org/W2963148242","https://openalex.org/W2964152930","https://openalex.org/W4231510805"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2160402959","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Analysing":[0],"topics":[1,29,62],"in":[2,30,81,93],"short":[3,15,46],"texts":[4,16,47],"(e.g.,":[5],"tweets":[6],"and":[7,98],"new":[8],"headings)":[9],"is":[10,24],"a":[11,41],"challenging":[12],"task":[13],"because":[14],"often":[17],"contain":[18],"insufficient":[19],"word":[20],"co-occurrence":[21],"information,":[22],"which":[23],"important":[25],"to":[26],"learn":[27],"good":[28],"conventional":[31],"topic":[32,99],"topics.":[33],"To":[34],"deal":[35],"with":[36],"the":[37,52,77,82],"insufficiency,":[38],"we":[39],"propose":[40],"generative":[42],"model":[43,57,89],"that":[44,87],"aggregates":[45],"into":[48],"clusters":[49],"by":[50,76],"leveraging":[51],"associated":[53],"meta":[54],"information.":[55],"Our":[56],"can":[58],"generate":[59],"more":[60],"interpretable":[61],"as":[63,65],"well":[64],"document":[66,96],"clusters.":[67],"We":[68],"develop":[69],"an":[70],"effective":[71],"Gibbs":[72],"sampling":[73],"algorithm":[74],"favoured":[75],"fully":[78],"local":[79],"conjugacy":[80],"model.":[83],"Extensive":[84],"experiments":[85],"demonstrate":[86],"our":[88],"achieves":[90],"better":[91],"performance":[92],"terms":[94],"of":[95],"clustering":[97],"coherence.":[100]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}