{"id":"https://openalex.org/W2746326396","doi":"https://doi.org/10.1007/s10115-017-1097-2","title":"The BigGrams: the semi-supervised information extraction system from HTML: an improvement in the wrapper induction","display_name":"The BigGrams: the semi-supervised information extraction system from HTML: an improvement in the wrapper induction","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2746326396","doi":"https://doi.org/10.1007/s10115-017-1097-2","mag":"2746326396"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-017-1097-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-017-1097-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10115-017-1097-2.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10115-017-1097-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017143339","display_name":"Marcin Miro\u0144czuk","orcid":"https://orcid.org/0000-0002-4951-2264"},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Marcin Micha\u0142 Miro\u0144czuk","raw_affiliation_strings":["Department of Artificial Intelligence, Institute of Computer Science Polish Academy of Sciences, Jana Kazimierza 5, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-4951-2264","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Institute of Computer Science Polish Academy of Sciences, Jana Kazimierza 5, Warsaw, Poland","institution_ids":["https://openalex.org/I99542240","https://openalex.org/I4210087266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017143339"],"corresponding_institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":3.5413,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93982313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"54","issue":"3","first_page":"711","last_page":"776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10260","display_name":"Software Engineering Research","score":0.973800003528595,"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/boosting","display_name":"Boosting (machine learning)","score":0.8809496164321899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982760667800903},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7069945335388184},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5295014381408691},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4463644027709961},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4201831817626953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3050093650817871}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8809496164321899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982760667800903},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7069945335388184},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5295014381408691},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4463644027709961},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4201831817626953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3050093650817871},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-017-1097-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-017-1097-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10115-017-1097-2.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10115-017-1097-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10115-017-1097-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10115-017-1097-2.pdf","source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G493603846","display_name":null,"funder_award_id":"UDA-POKL.04.01.01-00-051/10-00","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"},{"id":"https://openalex.org/G504991989","display_name":null,"funder_award_id":"UDA-POKL.04.01.01-00-051/10-00","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5110410658","display_name":null,"funder_award_id":"Agreement UDA-POKL.04.01.01-00-051/10-00","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"},{"id":"https://openalex.org/G544017953","display_name":null,"funder_award_id":"POKL.04.01.01-00-051/10-00","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2746326396.pdf","grobid_xml":"https://content.openalex.org/works/W2746326396.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W3419190","https://openalex.org/W18748505","https://openalex.org/W73047869","https://openalex.org/W86887328","https://openalex.org/W197270748","https://openalex.org/W331574839","https://openalex.org/W767037412","https://openalex.org/W1041723562","https://openalex.org/W1475104872","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1494776307","https://openalex.org/W1509392121","https://openalex.org/W1510658799","https://openalex.org/W1512387364","https://openalex.org/W1519606823","https://openalex.org/W1532325895","https://openalex.org/W1548492051","https://openalex.org/W1598223721","https://openalex.org/W1847921443","https://openalex.org/W1982242209","https://openalex.org/W1983498087","https://openalex.org/W1999361961","https://openalex.org/W2009591769","https://openalex.org/W2012399664","https://openalex.org/W2018985087","https://openalex.org/W2019254124","https://openalex.org/W2024091454","https://openalex.org/W2024428474","https://openalex.org/W2024791376","https://openalex.org/W2027081355","https://openalex.org/W2029537714","https://openalex.org/W2029580144","https://openalex.org/W2040757233","https://openalex.org/W2065568440","https://openalex.org/W2075100598","https://openalex.org/W2081020307","https://openalex.org/W2092126505","https://openalex.org/W2097874932","https://openalex.org/W2100059775","https://openalex.org/W2103931177","https://openalex.org/W2107391405","https://openalex.org/W2117510361","https://openalex.org/W2127978399","https://openalex.org/W2134150392","https://openalex.org/W2134172329","https://openalex.org/W2139423731","https://openalex.org/W2148317291","https://openalex.org/W2148540243","https://openalex.org/W2154444297","https://openalex.org/W2157215008","https://openalex.org/W2160196229","https://openalex.org/W2161861392","https://openalex.org/W2167200461","https://openalex.org/W2170505850","https://openalex.org/W2215206286","https://openalex.org/W2249963237","https://openalex.org/W2251623545","https://openalex.org/W2294680653","https://openalex.org/W2296045323","https://openalex.org/W2296061027","https://openalex.org/W2296164608","https://openalex.org/W2472280397","https://openalex.org/W2474670010","https://openalex.org/W2505770036","https://openalex.org/W2512255124","https://openalex.org/W2520480447","https://openalex.org/W2554915206","https://openalex.org/W2573020254","https://openalex.org/W2882319491","https://openalex.org/W2912557233","https://openalex.org/W2913389685","https://openalex.org/W3016230452","https://openalex.org/W4213009331","https://openalex.org/W4251302245","https://openalex.org/W4298345797"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W1566995892","https://openalex.org/W2583763619"],"abstract_inverted_index":{"The":[0,51],"aim":[1],"of":[2,75,78,94,108],"this":[3,34,67,95],"study":[4],"is":[5,15],"to":[6,17,60],"propose":[7],"an":[8],"information":[9,22,62,80,85,120],"extraction":[10,63,81,86,121],"system,":[11],"called":[12],"BigGrams,":[13],"which":[14],"able":[16],"retrieve":[18],"relevant":[19],"and":[20,45,88,110],"structural":[21],"(relevant":[23],"phrases,":[24],"keywords)":[25],"from":[26],"semi-structural":[27],"web":[28],"pages,":[29],"i.e.":[30,134],"HTML":[31,112],"documents.":[32],"For":[33],"purpose,":[35],"a":[36,56],"novel":[37],"semi-supervised":[38],"wrappers":[39,52],"induction":[40,53],"algorithm":[41,54],"has":[42],"been":[43],"developed":[44],"embedded":[46],"in":[47,66],"the":[48,69,73,76,79,91,101,105,111,124],"BigGrams":[49],"system.":[50,96],"utilizes":[55],"formal":[57],"concept":[58],"analysis":[59],"induce":[61],"patterns.":[64],"Also,":[65,123],"article,":[68],"author":[70,102],"(1)":[71],"presents":[72],"impact":[74],"configuration":[77],"system":[82],"components":[83],"on":[84,98],"results":[87],"(2)":[89],"tests":[90],"boosting":[92,125],"mode":[93,126],"Based":[97],"empirical":[99],"research,":[100],"established":[103],"that":[104],"proposed":[106],"taxonomy":[107],"seeds":[109],"tags":[113],"level":[114],"analysis,":[115],"with":[116],"appropriate":[117],"pre-processing,":[118],"improve":[119],"results.":[122],"works":[127],"well":[128],"when":[129,135],"certain":[130],"requirements":[131],"are":[132,139],"met,":[133],"well-diversified":[136],"input":[137],"data":[138],"ensured.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}