{"id":"https://openalex.org/W4404132388","doi":"https://doi.org/10.1162/tacl_a_00712","title":"Self-supervised Topic Taxonomy Discovery in the Box Embedding Space","display_name":"Self-supervised Topic Taxonomy Discovery in the Box Embedding Space","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404132388","doi":"https://doi.org/10.1162/tacl_a_00712"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00712","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00712","pdf_url":null,"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":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl_a_00712","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049632474","display_name":"Yuyin Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyin Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. luyy37@mail2.sysu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. luyy37@mail2.sysu.edu.cn","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025168035","display_name":"Hegang Chen","orcid":"https://orcid.org/0000-0001-8338-3884"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hegang Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. chenhg25@mail2.sysu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. chenhg25@mail2.sysu.edu.cn","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112974305","display_name":"Pengbo Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengbo Mao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. maopb@mail2.sysu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. maopb@mail2.sysu.edu.cn","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797069","display_name":"Yanghui Rao","orcid":"https://orcid.org/0000-0002-2887-8056"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghui Rao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. raoyangh@mail.sysu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China. raoyangh@mail.sysu.edu.cn","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013151488","display_name":"Haoran Xie","orcid":"https://orcid.org/0000-0003-0965-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Xie","raw_affiliation_strings":["School of Data Science, Lingnan University, Hong Kong SAR. hrxie@ieee.org"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Lingnan University, Hong Kong SAR. hrxie@ieee.org","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482402","display_name":"Fu Lee Wang","orcid":"https://orcid.org/0000-0002-3976-0053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu Lee Wang","raw_affiliation_strings":["School of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR. pwang@hkmu.edu.hk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR. pwang@hkmu.edu.hk","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, the Hong Kong Polytechnic University, Hong Kong SAR. csqli@comp.polyu.edu.hk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, the Hong Kong Polytechnic University, Hong Kong SAR. csqli@comp.polyu.edu.hk","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81863586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1401","last_page":"1416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.993399977684021,"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":0.8173109292984009},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.7028159499168396},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6294443607330322},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5546337366104126},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48040178418159485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4793035089969635},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45142924785614014},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37862488627433777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173109292984009},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.7028159499168396},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6294443607330322},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5546337366104126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48040178418159485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4793035089969635},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45142924785614014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37862488627433777},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl_a_00712","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00712","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00712","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00712","pdf_url":null,"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","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1989492805","https://openalex.org/W2003899488","https://openalex.org/W2081580037","https://openalex.org/W2093257937","https://openalex.org/W2122678284","https://openalex.org/W2132827946","https://openalex.org/W2165232124","https://openalex.org/W2226402862","https://openalex.org/W2250533720","https://openalex.org/W2250539671","https://openalex.org/W2285986798","https://openalex.org/W2482589566","https://openalex.org/W2883559670","https://openalex.org/W2891420675","https://openalex.org/W2903908313","https://openalex.org/W2952576857","https://openalex.org/W2962784289","https://openalex.org/W2963690776","https://openalex.org/W3034608479","https://openalex.org/W3034735823","https://openalex.org/W3042602466","https://openalex.org/W3045464143","https://openalex.org/W3100651519","https://openalex.org/W3105538385","https://openalex.org/W3114316021","https://openalex.org/W3160346047","https://openalex.org/W3177067286","https://openalex.org/W3207972072","https://openalex.org/W3217015614","https://openalex.org/W4220771481","https://openalex.org/W4221142221","https://openalex.org/W4224315235","https://openalex.org/W4224326644","https://openalex.org/W4231510805","https://openalex.org/W4307011241","https://openalex.org/W4365394984","https://openalex.org/W4379933553","https://openalex.org/W6637131181","https://openalex.org/W6639619044","https://openalex.org/W6639732818","https://openalex.org/W6668990524","https://openalex.org/W6683333316","https://openalex.org/W6739076403","https://openalex.org/W6755207826","https://openalex.org/W6757037870","https://openalex.org/W6780896692","https://openalex.org/W6784187067","https://openalex.org/W6796976259","https://openalex.org/W6802492322","https://openalex.org/W6803182808","https://openalex.org/W6810311456"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Abstract":[0],"Topic":[1,80],"taxonomy":[2,133],"discovery":[3],"aims":[4],"at":[5,62],"uncovering":[6],"topics":[7,30,61,87,112,118],"of":[8,27,59,130],"different":[9],"abstraction":[10,64],"levels":[11,65],"and":[12,29,66,86],"constructing":[13],"hierarchical":[14,43,68,102],"relations":[15,44,103],"between":[16,48,116],"them.":[17],"Unfortunately,":[18],"most":[19],"prior":[20],"work":[21],"can":[22],"hardly":[23],"model":[24],"semantic":[25],"scopes":[26],"words":[28,85],"by":[31,45,135],"holding":[32],"the":[33,89,94,131],"Euclidean":[34],"embedding":[35,91],"space":[36],"assumption.":[37],"What\u2019s":[38],"worse,":[39],"they":[40],"infer":[41,101],"asymmetric":[42,95],"symmetric":[46],"distances":[47],"topic":[49,123,132],"embeddings.":[50],"As":[51],"a":[52,77],"result,":[53],"existing":[54],"methods":[55],"suffer":[56],"from":[57],"problems":[58],"low-quality":[60],"high":[63],"inaccurate":[67],"relations.":[69],"To":[70],"alleviate":[71],"these":[72],"problems,":[73],"this":[74],"paper":[75],"develops":[76],"Box":[78],"embedding-based":[79],"Model":[81],"(BoxTM)":[82],"that":[83],"maps":[84],"into":[88],"box":[90],"space,":[92],"where":[93],"metric":[96],"is":[97],"defined":[98],"to":[99],"properly":[100],"among":[104],"topics.":[105],"Additionally,":[106],"our":[107],"BoxTM":[108],"explicitly":[109],"infers":[110],"upper-level":[111],"based":[113],"on":[114,122],"correlation":[115],"specific":[117],"through":[119],"recursive":[120],"clustering":[121],"boxes.":[124],"Finally,":[125],"extensive":[126],"experiments":[127],"validate":[128],"high-quality":[129],"learned":[134],"BoxTM.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}