{"id":"https://openalex.org/W1997060871","doi":"https://doi.org/10.1109/icmlc.2010.5580698","title":"An information extraction system for heterogeneous Web source","display_name":"An information extraction system for heterogeneous Web source","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W1997060871","doi":"https://doi.org/10.1109/icmlc.2010.5580698","mag":"1997060871"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2010.5580698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2010.5580698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Machine Learning 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/A5008363243","display_name":"Ting Zhou","orcid":"https://orcid.org/0000-0001-7096-7610"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Zhou","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033705258","display_name":"Chengjie Sun","orcid":"https://orcid.org/0000-0001-9081-1410"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng-Jie Sun","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048326379","display_name":"Lei Lin","orcid":"https://orcid.org/0000-0002-1161-8565"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Lin","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Quan Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"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":null,"issue":null,"first_page":"3287","last_page":"3292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9702000021934509,"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/T13976","display_name":"Web visibility and informetrics","score":0.9702000021934509,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827682375907898},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.700512170791626},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6422951221466064},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6165332198143005},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5444799661636353},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.524967610836029},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.47702571749687195},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.4533114731311798},{"id":"https://openalex.org/keywords/information-source","display_name":"Information source (mathematics)","score":0.45054399967193604},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25666236877441406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10860240459442139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827682375907898},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.700512170791626},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6422951221466064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6165332198143005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5444799661636353},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.524967610836029},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.47702571749687195},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.4533114731311798},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.45054399967193604},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25666236877441406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10860240459442139},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2010.5580698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2010.5580698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1530994416","https://openalex.org/W1599188306","https://openalex.org/W1600320866","https://openalex.org/W1981791873","https://openalex.org/W1986398135","https://openalex.org/W2023094000","https://openalex.org/W2029296527","https://openalex.org/W2069140227","https://openalex.org/W2096496923","https://openalex.org/W2105948726","https://openalex.org/W2113958117","https://openalex.org/W2114544510","https://openalex.org/W2120814856","https://openalex.org/W2127978399","https://openalex.org/W2134150392","https://openalex.org/W2145948275","https://openalex.org/W2148540243","https://openalex.org/W2162340487","https://openalex.org/W2162590473","https://openalex.org/W2163362093","https://openalex.org/W4285719527","https://openalex.org/W6635684370","https://openalex.org/W6681762687","https://openalex.org/W6683883671"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W2099413755","https://openalex.org/W2108905092","https://openalex.org/W2103771357","https://openalex.org/W819512689","https://openalex.org/W2125792968","https://openalex.org/W4387668946","https://openalex.org/W186203689","https://openalex.org/W2368184689"],"abstract_inverted_index":{"Information":[0],"Extraction":[1],"is":[2,43],"the":[3,29,41,47,85,96,99],"task":[4],"of":[5,31,40,98],"identifying":[6],"information":[7,23,30,49,74,78],"in":[8,35,92],"texts":[9],"and":[10,53,77],"converting":[11],"it":[12],"into":[13,56],"a":[14],"predefined":[15],"format.":[16,58],"In":[17],"this":[18],"paper,":[19],"we":[20],"build":[21],"an":[22],"integration":[24],"system":[25,42,60,86],"which":[26,94],"focuses":[27],"on":[28],"computer":[32],"science":[33],"teachers":[34],"Chinese":[36],"universities.":[37],"The":[38,59],"target":[39],"to":[44,87],"automatically":[45],"extract":[46],"useful":[48],"from":[50],"heterogeneous":[51],"sources":[52],"re-organize":[54],"them":[55],"structured":[57],"includes":[61],"4":[62],"main":[63],"modules:":[64],"web":[65,69],"pages":[66],"retrieval":[67],"module,":[68,73],"pages'":[70],"structure":[71],"classification":[72],"extraction":[75],"module":[76],"updating":[79],"module.":[80],"We":[81],"have":[82],"successfully":[83],"applied":[84],"deal":[88],"with":[89],"107":[90],"universities":[91],"China":[93],"shows":[95],"effect":[97],"proposed":[100],"system.":[101]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}