{"id":"https://openalex.org/W2137769856","doi":"https://doi.org/10.1109/icsmc.2007.4413834","title":"Extracting domain-specific terms from unlabeled web documents by bootstrapping and term classifiers","display_name":"Extracting domain-specific terms from unlabeled web documents by bootstrapping and term classifiers","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2137769856","doi":"https://doi.org/10.1109/icsmc.2007.4413834","mag":"2137769856"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2007.4413834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4413834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008976636","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0002-9398-7005"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","Harbin Institute of Technology, Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424262","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0002-5549-5560"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Long Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","Harbin Institute of Technology, Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004324294","display_name":"Bingquan Liu","orcid":"https://orcid.org/0000-0001-6352-2170"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Quan Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","Harbin Institute of Technology, Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881571","display_name":"Yuanchao Liu","orcid":"https://orcid.org/0009-0007-0430-7658"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan-Chao Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","Harbin Institute of Technology, Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114833165","display_name":"LI Ming-hui","orcid":"https://orcid.org/0000-0003-4750-0435"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Hui Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","Harbin Institute of Technology, Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"3875","last_page":"3880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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":0.9955000281333923,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9954000115394592,"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":0.7989994287490845},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7066943645477295},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6919248104095459},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6631284356117249},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6269460320472717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5742480754852295},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5598071217536926},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48374462127685547},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45112648606300354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3812524080276489},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3488767147064209},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13090792298316956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989994287490845},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7066943645477295},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6919248104095459},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6631284356117249},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6269460320472717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742480754852295},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5598071217536926},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48374462127685547},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45112648606300354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3812524080276489},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3488767147064209},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13090792298316956},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2007.4413834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2007.4413834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W10597021","https://openalex.org/W79835312","https://openalex.org/W123384503","https://openalex.org/W318961524","https://openalex.org/W1520020608","https://openalex.org/W2015288652","https://openalex.org/W2074537787","https://openalex.org/W2118714763","https://openalex.org/W2123708594","https://openalex.org/W2138916604","https://openalex.org/W2147865945","https://openalex.org/W2158997610","https://openalex.org/W2166843810","https://openalex.org/W4255991504","https://openalex.org/W6600417476","https://openalex.org/W6603251921","https://openalex.org/W6604953587","https://openalex.org/W6611162344","https://openalex.org/W6680529873"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W156620619","https://openalex.org/W2616249226","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W1598221548","https://openalex.org/W2081850291","https://openalex.org/W1963695443","https://openalex.org/W4387366173"],"abstract_inverted_index":{"Domain-specific":[0],"term":[1,32,45,50,54,90,101,144],"extraction":[2,51,102,145],"contributes":[3],"to":[4,34,83],"all":[5],"domain-oriented":[6],"natural":[7],"language":[8],"processing":[9],"tasks.":[10],"Given":[11],"a":[12,31,53,56],"small":[13],"set":[14],"of":[15,59,64,77,112,121],"domain-specific":[16,49,100,143],"terms":[17,22,40,65,78,82,113,122,165],"as":[18],"seed":[19,39],"terms,":[20],"new":[21,42,89],"from":[23],"unlabeled":[24],"corpora":[25,128],"can":[26],"be":[27],"extracted":[28,81],"by":[29,131],"bootstrapping":[30],"classifier":[33],"discover":[35],"the":[36,74,110,141,170],"association":[37,63,111],"between":[38],"and":[41,79,126],"terms.":[43],"Traditional":[44],"representation":[46,71,91,107,150,155],"method":[47,92,146,153],"for":[48,99,162,169],"represents":[52],"in":[55,85,93,103,157],"feature":[57],"space":[58,96],"documents,":[60],"which":[61,66,114],"depicts":[62,109],"share":[67,115],"common":[68,116],"documents.":[69,87],"This":[70,106],"can't":[72],"depict":[73],"inner-document":[75],"information":[76,120],"requires":[80],"occur":[84],"multiple":[86],"A":[88],"global":[94,117,132,148],"contextual":[95,149],"is":[97,129,166],"proposed":[98,142,171],"this":[104],"paper.":[105],"mechanism":[108,156],"contexts.":[118,133],"The":[119,160],"within":[123],"certain":[124],"document":[125],"among":[127],"depicted":[130],"Experiments":[134],"on":[135],"Chinese":[136],"web":[137],"corpus":[138],"show":[139],"that":[140],"with":[147,154],"outperforms":[151],"traditional":[152],"documents":[158],"space.":[159],"improvement":[161],"low":[163],"frequency":[164],"much":[167],"higher":[168],"method.":[172]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}