{"id":"https://openalex.org/W2507537540","doi":"https://doi.org/10.18653/v1/p16-1110","title":"ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling","display_name":"ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2507537540","doi":"https://doi.org/10.18653/v1/p16-1110","mag":"2507537540"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1110","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1110","pdf_url":"https://www.aclweb.org/anthology/P16-1110.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-1110.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050672404","display_name":"Forough Poursabzi-Sangdeh","orcid":null},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forough Poursabzi-Sangdeh","raw_affiliation_strings":["Computer Science University of Colorado"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science University of Colorado","institution_ids":["https://openalex.org/I2802236040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081307846","display_name":"Jordan Boyd\u2010Graber","orcid":"https://orcid.org/0000-0002-7770-4431"},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordan Boyd-Graber","raw_affiliation_strings":["Computer Science University of Colorado"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science University of Colorado","institution_ids":["https://openalex.org/I2802236040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031744461","display_name":"Leah Findlater","orcid":"https://orcid.org/0000-0002-5619-4452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leah Findlater","raw_affiliation_strings":["iSchool and UMIACS University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iSchool and UMIACS University of Maryland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029074659","display_name":"Kevin Seppi","orcid":"https://orcid.org/0000-0002-4932-2700"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Seppi","raw_affiliation_strings":["Computer Science Brigham Young University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Brigham Young University","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9748,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1158","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9976999759674072,"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":0.9955000281333923,"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":0.8419713973999023},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.6705833673477173},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6255267858505249},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5953655242919922},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49273112416267395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663397967815399},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4175843596458435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38522017002105713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419713973999023},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.6705833673477173},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6255267858505249},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5953655242919922},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49273112416267395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663397967815399},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4175843596458435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38522017002105713},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-1110","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1110","pdf_url":"https://www.aclweb.org/anthology/P16-1110.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1110","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1110","pdf_url":"https://www.aclweb.org/anthology/P16-1110.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G2438599531","display_name":"Collaborative Research: Scaling Insight into Science: Assessing the value and effectiveness of machine assisted classification within a statistical system","funder_award_id":"1422492","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4331084930","display_name":"III: Medium: Collaborative Research: Closing the User-Model Loop for Understanding Topics in Large Document Collections","funder_award_id":"1409739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5264030819","display_name":"III: Medium: Collaborative Research: Closing the User-Model Loop for Understanding Topics in Large Document Collections","funder_award_id":"1409287","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6217427624","display_name":null,"funder_award_id":"IIS-1409287","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7679064062","display_name":null,"funder_award_id":"NCSE-1422492","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2507537540.pdf","grobid_xml":"https://content.openalex.org/works/W2507537540.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W76930416","https://openalex.org/W89222448","https://openalex.org/W173861811","https://openalex.org/W628052711","https://openalex.org/W644964750","https://openalex.org/W1591954893","https://openalex.org/W1782524086","https://openalex.org/W1803273808","https://openalex.org/W1880262756","https://openalex.org/W1965382725","https://openalex.org/W1969486090","https://openalex.org/W1970381522","https://openalex.org/W2010588484","https://openalex.org/W2016196732","https://openalex.org/W2024722304","https://openalex.org/W2033403400","https://openalex.org/W2042932437","https://openalex.org/W2065010255","https://openalex.org/W2074449313","https://openalex.org/W2080021732","https://openalex.org/W2085989833","https://openalex.org/W2087382273","https://openalex.org/W2096974619","https://openalex.org/W2098062695","https://openalex.org/W2101101940","https://openalex.org/W2102610131","https://openalex.org/W2112422413","https://openalex.org/W2113499583","https://openalex.org/W2128213565","https://openalex.org/W2129070834","https://openalex.org/W2148426685","https://openalex.org/W2157289187","https://openalex.org/W2157821464","https://openalex.org/W2166496241","https://openalex.org/W2250355330","https://openalex.org/W2250533720","https://openalex.org/W2251738400","https://openalex.org/W2294709184","https://openalex.org/W2400219830","https://openalex.org/W2788290136","https://openalex.org/W2803437449","https://openalex.org/W2949435794","https://openalex.org/W3139328003","https://openalex.org/W4231510805","https://openalex.org/W4244030505","https://openalex.org/W4255428302","https://openalex.org/W4281564584","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2914897824","https://openalex.org/W4224256816","https://openalex.org/W2183624479","https://openalex.org/W2759744443","https://openalex.org/W4206195464","https://openalex.org/W2041249487"],"abstract_inverted_index":{"Effective":[0],"text":[1],"classification":[2],"requires":[3],"experts":[4],"to":[5,17,50,66,80,87,91,116],"annotate":[6,69],"data":[7,12],"with":[8,60],"labels;":[9],"these":[10],"training":[11],"are":[13],"time-consuming":[14],"and":[15,82,120],"expensive":[16],"obtain.":[18],"If":[19],"you":[20,24],"know":[21],"what":[22,78],"labels":[23,79],"want,":[25],"active":[26,83,100],"learning":[27,84,101],"can":[28],"reduce":[29],"the":[30,38,46,88],"number":[31],"of":[32,77],"labeled":[33],"documents":[34,90],"needed.":[35],"However,":[36],"establishing":[37],"label":[39,53,118],"set":[40],"remains":[41],"difficult.":[42],"Annotators":[43],"often":[44],"lack":[45],"global":[47,75],"knowledge":[48],"needed":[49],"induce":[51],"a":[52,74],"set.":[54],"We":[55],"introduce":[56],"ALTO:":[57],"Active":[58],"Learning":[59],"Topic":[61],"Overviews,":[62],"an":[63],"interactive":[64],"system":[65],"help":[67],"humans":[68],"documents:":[70],"topic":[71,110],"models":[72,111],"provide":[73],"overview":[76],"create":[81],"directs":[85],"them":[86],"right":[89],"label.":[92],"Our":[93],"forty-annotator":[94],"user":[95],"study":[96],"shows":[97],"that":[98],"while":[99],"alone":[102],"is":[103,123],"best":[104,124],"in":[105],"extremely":[106],"resource":[107],"limited":[108],"conditions,":[109],"(even":[112],"by":[113],"themselves)":[114],"lead":[115],"better":[117],"sets,":[119],"ALTO's":[121],"combination":[122],"overall.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}