{"id":"https://openalex.org/W1620204465","doi":null,"title":"Hierarchically Classifying Documents Using Very Few Words","display_name":"Hierarchically Classifying Documents Using Very Few Words","publication_year":1997,"publication_date":"1997-07-08","ids":{"openalex":"https://openalex.org/W1620204465","mag":"1620204465"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.988","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Carl_Staelin/cs236601/koller97.ps.gz","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5051658526","display_name":"Daphne Koller","orcid":"https://orcid.org/0000-0002-2361-6479","observed_orcids":["https://orcid.org/0000-0002-2361-6479","https://orcid.org/0009-0007-1645-951X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daphne Koller","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2361-6479","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054695014","display_name":"Mehran Sahami","orcid":"https://orcid.org/0000-0001-9549-6974","observed_orcids":["https://orcid.org/0000-0001-9549-6974"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehran Sahami","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9549-6974","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.5893,"has_fulltext":false,"cited_by_count":854,"citation_normalized_percentile":{"value":0.99703947,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.0,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hierarchical-text-classification","display_name":"hierarchical text classification","score":0.9139999747276306},{"id":"https://openalex.org/keywords/topic-hierarchy","display_name":"topic hierarchy","score":0.968999981880188},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.5429999828338623},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025373816490173},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7633955478668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6206597685813904},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.554151713848114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5480282306671143},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5153288245201111},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4531562030315399},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.45231834053993225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44567230343818665},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.44151052832603455},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3906533718109131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34588658809661865},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15291795134544373},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.988","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Carl_Staelin/cs236601/koller97.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.31.2455","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.2455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/users/daphne/papers/ml97.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.44.4991","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.44.4991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-diglib.stanford.edu/diglib/WP/PUBLIC/DOC130.ps","raw_type":"text"},{"id":"mag:1620204465","doi":null,"is_oa":false,"landing_page_url":"http://dbpubs.stanford.edu:8090/pub/1997-75","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1525398599","https://openalex.org/W7100974794","https://openalex.org/W7099960116","https://openalex.org/W7097309196","https://openalex.org/W2161185282","https://openalex.org/W4235768290","https://openalex.org/W2073830447","https://openalex.org/W7098161158","https://openalex.org/W7098445216","https://openalex.org/W2014566476"],"abstract_inverted_index":{"The":[0,151],"proliferation":[1],"of":[2,51,57,83,98,114,125,153],"topic":[3,73],"hierarchies":[4],"for":[5,13],"text":[6,42],"documents":[7,19],"has":[8],"resulted":[9],"in":[10,41,90],"a":[11,48,54,81,110,148],"need":[12],"tools":[14],"that":[15,69],"automatically":[16],"classify":[17],"new":[18],"within":[20],"such":[21],"hierarchies.":[22],"Existing":[23],"classification":[24,43,78,92],"schemes":[25],"which":[26],"ignore":[27],"the":[28,33,45,71,77,91,119,131,136],"hierarchical":[29,72],"structure":[30,74],"and":[31,53],"treat":[32],"topics":[34],"as":[35],"separate":[36],"classes":[37,52],"are":[38],"often":[39],"inadequate":[40],"where":[44],"there":[46],"is":[47],"large":[49],"number":[50,56],"huge":[55],"relevant":[58,117,126,138],"features":[59,127],"needed":[60],"to":[61,75,118,159],"distinguish":[62],"between":[63],"them.":[64],"We":[65],"propose":[66],"an":[67],"approach":[68],"utilizes":[70],"decompose":[76],"task":[79,120],"into":[80],"set":[82,113,124,140],"simpler":[84],"problems,":[85],"one":[86],"at":[87,121],"each":[88,97,144],"node":[89],"tree.":[93],"As":[94],"we":[95],"show,":[96],"these":[99],"smaller":[100],"problems":[101],"can":[102],"be":[103,142],"solved":[104],"accurately":[105],"by":[106],"focusing":[107],"only":[108,146],"on":[109],"very":[111],"small":[112,149],"features,":[115],"those":[116],"hand.":[122],"This":[123],"varies":[128],"widely":[129],"throughout":[130],"hierarchy,":[132],"so":[133],"that,":[134],"while":[135],"overall":[137],"feature":[139,155],"may":[141],"large,":[143],"classifier":[145],"examines":[147],"subset.":[150],"use":[152],"reduced":[154],"sets":[156],"allows":[157],"us":[158],"util...":[160]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":36},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":47}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}