{"id":"https://openalex.org/W4385574337","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.115","title":"Seeded Hierarchical Clustering for Expert-Crafted Taxonomies","display_name":"Seeded Hierarchical Clustering for Expert-Crafted Taxonomies","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385574337","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.115"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.findings-emnlp.115","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.115","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.findings-emnlp.115","pdf_url":"https://aclanthology.org/2022.findings-emnlp.115.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2022","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.findings-emnlp.115.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103257617","display_name":"Anish Saha","orcid":"https://orcid.org/0000-0002-5102-6943","observed_orcids":["https://orcid.org/0000-0002-5102-6943"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anish Saha","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000658547","display_name":"Amith Ananthram","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amith Ananthram","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008920438","display_name":"Emily Allaway","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Allaway","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966","observed_orcids":["https://orcid.org/0000-0002-0464-7966"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109565051","display_name":"Kathleen R. McKeown","orcid":"https://orcid.org/0000-0003-4455-2715","observed_orcids":["https://orcid.org/0000-0003-4455-2715"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen McKeown","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1048,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.25010772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1595","last_page":"1609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9077000021934509,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9077000021934509,"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":0.0348999984562397,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.030700000002980232,"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/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/topic-assignment","display_name":"topic assignment","score":0.5400000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867686152458191},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7446202635765076},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6287238001823425},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6133145689964294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5707077980041504},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5491077303886414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42231640219688416},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4199961721897125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3492918610572815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3385634422302246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10077762603759766},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2022.findings-emnlp.115","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.115","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.findings-emnlp.115","pdf_url":"https://aclanthology.org/2022.findings-emnlp.115.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.11602","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.11602","pdf_url":"https://arxiv.org/pdf/2205.11602","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/70368e4a-3f4d-4284-ac67-2d9a18594c60","doi":null,"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/470042399/SeededHierarchicalClustering_final_published_version_conference_contribution_.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2205.11602","doi":"https://doi.org/10.48550/arxiv.2205.11602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.11602","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.findings-emnlp.115","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.115","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.findings-emnlp.115","pdf_url":"https://aclanthology.org/2022.findings-emnlp.115.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1163247334","display_name":null,"funder_award_id":"DGE 16?44869","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4818418728","display_name":null,"funder_award_id":"FA8750-18-2-0014","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5551450873","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1644869","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385574337.pdf","grobid_xml":"https://content.openalex.org/works/W4385574337.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W56136284","https://openalex.org/W151377110","https://openalex.org/W1620204465","https://openalex.org/W1880262756","https://openalex.org/W1977224551","https://openalex.org/W1996227995","https://openalex.org/W2061922307","https://openalex.org/W2068737686","https://openalex.org/W2102524069","https://openalex.org/W2105456431","https://openalex.org/W2117173982","https://openalex.org/W2117510361","https://openalex.org/W2127218421","https://openalex.org/W2132827946","https://openalex.org/W2138615112","https://openalex.org/W2150102617","https://openalex.org/W2150593711","https://openalex.org/W2150766729","https://openalex.org/W2153383412","https://openalex.org/W2250539671","https://openalex.org/W2468328197","https://openalex.org/W2559613745","https://openalex.org/W2759474451","https://openalex.org/W2890362944","https://openalex.org/W2903908313","https://openalex.org/W2913869196","https://openalex.org/W2965373594","https://openalex.org/W2980384207","https://openalex.org/W3034735823","https://openalex.org/W3035690777","https://openalex.org/W3042602466","https://openalex.org/W3158986179","https://openalex.org/W3171416056","https://openalex.org/W3201098653","https://openalex.org/W4220771481","https://openalex.org/W4221151676"],"related_works":["https://openalex.org/W4237723370","https://openalex.org/W7009378368","https://openalex.org/W2162092316","https://openalex.org/W2115620960","https://openalex.org/W2952522726","https://openalex.org/W2294607801","https://openalex.org/W2142726736","https://openalex.org/W1573498282","https://openalex.org/W1995233974","https://openalex.org/W4220771481"],"abstract_inverted_index":{"Practitioners":[0],"from":[1],"many":[2],"disciplines":[3],"(e.g.,":[4],"political":[5],"science)":[6],"use":[7],"expert-crafted":[8],"taxonomies":[9,34],"to":[10,32,71],"make":[11],"sense":[12],"of":[13,27,40,59],"large,":[14],"unlabeled":[15,30],"corpora.In":[16],"this":[17,51],"work,":[18],"we":[19],"study":[20],"Seeded":[21],"Hierarchical":[22],"Clustering":[23],"(SHC):":[24],"the":[25,88],"task":[26,52,90],"automatically":[28],"fitting":[29],"data":[31,65],"such":[33],"using":[35],"only":[36,55],"a":[37,45,56],"small":[38,57],"set":[39,58],"labeled":[41,60],"examples.We":[42],"propose":[43],"HI-ERSEED,":[44],"novel":[46],"weakly":[47],"supervised":[48,85],"algorithm":[49],"for":[50,87],"that":[53],"uses":[54],"seed":[61],"examples.It":[62],"is":[63],"both":[64,82],"and":[66,84],"computationally":[67],"efficient.HIERSEED":[68],"assigns":[69],"documents":[70],"topics":[72],"by":[73],"weighing":[74],"document":[75],"density":[76],"against":[77],"topic":[78],"hierarchical":[79],"structure.It":[80],"outperforms":[81],"unsupervised":[83],"baselines":[86],"SHC":[89],"on":[91],"three":[92],"real-world":[93],"datasets.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-05T00:00:00"}