{"id":"https://openalex.org/W2003690014","doi":"https://doi.org/10.1017/s1351324902002899","title":"Selecting effective index terms using a decision tree","display_name":"Selecting effective index terms using a decision tree","publication_year":2002,"publication_date":"2002-06-01","ids":{"openalex":"https://openalex.org/W2003690014","doi":"https://doi.org/10.1017/s1351324902002899","mag":"2003690014"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324902002899","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324902002899","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5057761218","display_name":"Takenobu Tokunaga","orcid":"https://orcid.org/0000-0002-1399-9517"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"TOKUNAGA TAKENOBU","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735103","display_name":"Kenji Kimura","orcid":"https://orcid.org/0009-0002-9020-077X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"KIMURA KENJI","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019149834","display_name":"OGIBAYASHI HIRONORI","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"OGIBAYASHI HIRONORI","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105286529","display_name":"Hozumi Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"TANAKA HOZUMI","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057761218"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.8526,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7711991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"2-3","first_page":"193","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991999864578247,"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/T10215","display_name":"Semantic Web and Ontologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8753476142883301},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6980199217796326},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6030792593955994},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.49624162912368774},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.46004796028137207},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4482915997505188},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4245494604110718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42131882905960083},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4114193618297577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3833481967449188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09814098477363586},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.05748435854911804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8753476142883301},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6980199217796326},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6030792593955994},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.49624162912368774},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.46004796028137207},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4482915997505188},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4245494604110718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42131882905960083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4114193618297577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3833481967449188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09814098477363586},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.05748435854911804},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324902002899","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324902002899","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00070861","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100467008","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00080923","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100477334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W69295931","https://openalex.org/W95284390","https://openalex.org/W1515852583","https://openalex.org/W1570542661","https://openalex.org/W1632114991","https://openalex.org/W1658342862","https://openalex.org/W1965282483","https://openalex.org/W2032083037","https://openalex.org/W2045577803","https://openalex.org/W2073826624","https://openalex.org/W2144211451","https://openalex.org/W3037581684"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2348097614","https://openalex.org/W2103338134","https://openalex.org/W2094492371","https://openalex.org/W2358841807","https://openalex.org/W2738041616","https://openalex.org/W2036641180","https://openalex.org/W1975278352","https://openalex.org/W83344948","https://openalex.org/W2369213182"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,11,27,39,58,61,66,69,78,118,131],"effectiveness":[4,67,87,125],"of":[5,60,68,72,93,130],"index":[6,42,73,108],"terms":[7,43,74,109],"more":[8],"complex":[9,41],"than":[10],"single":[12,49],"words":[13,50],"used":[14],"in":[15,23,26,38,128],"conventional":[16,30],"information":[17,53],"retrieval":[18,31,86,124],"systems.":[19],"Retrieval":[20],"is":[21,36],"done":[22],"two":[24],"phases:":[25],"first,":[28],"a":[29,103,112],"method":[32,104],"(the":[33],"Okapi":[34],"system)":[35],"used;":[37],"second,":[40],"such":[44],"as":[45],"syntactic":[46],"relations":[47],"and":[48,82],"with":[51,117],"part-of-speech":[52],"are":[54],"introduced":[55],"to":[56,105],"rerank":[57],"results":[59],"first":[62],"phase.":[63],"We":[64],"evaluated":[65],"different":[70],"types":[71],"through":[75],"experiments":[76,116],"using":[77,111],"TREC-7":[79],"test":[80,120],"collection":[81,121],"50":[83,94,132],"queries.":[84,95,133],"The":[85],"was":[88,126],"improved":[89,127],"for":[90],"32":[91],"out":[92],"Based":[96],"on":[97],"this":[98],"investigation,":[99],"we":[100],"then":[101],"introduce":[102],"select":[106],"effective":[107],"by":[110],"decision":[113],"tree.":[114],"Further":[115],"same":[119],"showed":[122],"that":[123],"25":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
