{"id":"https://openalex.org/W2111322522","doi":"https://doi.org/10.1145/1062745.1062849","title":"Hybrid semantic tagging for information extraction","display_name":"Hybrid semantic tagging for information extraction","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2111322522","doi":"https://doi.org/10.1145/1062745.1062849","mag":"2111322522"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-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/A5111407570","display_name":"Ronen Feldman","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronen Feldman","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, ISRAEL","Bar-Ilan\u00a0University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, ISRAEL","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan\u00a0University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012200650","display_name":"Benjamin Rosenfeld","orcid":"https://orcid.org/0000-0002-0660-4046"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Benjamin Rosenfeld","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, ISRAEL","Bar-Ilan\u00a0University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, ISRAEL","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan\u00a0University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012260488","display_name":"Moshe Fresko","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Moshe Fresko","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, ISRAEL","Bar-Ilan\u00a0University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, ISRAEL","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan\u00a0University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042328810","display_name":"Brian D. Davison","orcid":"https://orcid.org/0000-0002-9326-3648"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian D. Davison","raw_affiliation_strings":["Lehigh University, Bethlehem, PA","Lehigh University Bethlehem PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University Bethlehem PA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14549619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1022","last_page":"1022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9919000267982483,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.982699990272522,"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":0.9016117453575134},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.6041437387466431},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5462169647216797},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.5043874979019165},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.49845194816589355},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49510064721107483},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4898025691509247},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.48240673542022705},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4815095365047455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4753299057483673},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4118371903896332},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23466810584068298},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.12188157439231873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9016117453575134},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.6041437387466431},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5462169647216797},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.5043874979019165},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.49845194816589355},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49510064721107483},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4898025691509247},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.48240673542022705},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4815095365047455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4753299057483673},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4118371903896332},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23466810584068298},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.12188157439231873},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1062745.1062849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.6424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.6424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.lehigh.edu/~brian/pubs/2005/www/feldmanwww05poster.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.8465","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.8465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p1022.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1520377376","https://openalex.org/W1934019294","https://openalex.org/W2161676054"],"related_works":["https://openalex.org/W2387349142","https://openalex.org/W1521613906","https://openalex.org/W2537839963","https://openalex.org/W3150576547","https://openalex.org/W2023110884","https://openalex.org/W2349698472","https://openalex.org/W1692244837","https://openalex.org/W2374532690","https://openalex.org/W2030891979","https://openalex.org/W2151801904"],"abstract_inverted_index":{"The":[0,92,123,164],"semantic":[1,31,41,58,64,221],"web":[2,32,37,218,222],"is":[3,54],"expected":[4],"to":[5,66,83,95,136,220],"have":[6],"an":[7,161],"impact":[8],"at":[9,88],"least":[10],"as":[11,13],"big":[12],"that":[14,48,167],"of":[15,44,60,103,111,125,145,182,191,199,204],"the":[16,25,40,45,57,63,68,89,99,109,126,197,211],"existing":[17,36],"HTML":[18],"based":[19,154],"web,":[20],"if":[21],"not":[22],"greater.":[23],"However,":[24],"challenge":[26],"lays":[27],"in":[28,34,51,147],"creating":[29],"this":[30],"and":[33,77,86,97,157,175,188],"converting":[35,216],"information":[38,79],"into":[39],"paradigm.":[42],"One":[43],"core":[46],"technologies":[47],"can":[49,133],"help":[50],"migration":[52],"process":[53],"automatic":[55],"markup,":[56],"markup":[59],"content,":[61],"providing":[62],"tags":[65],"describe":[67],"raw":[69],"content.":[70],"This":[71,209],"paper":[72],"describes":[73],"a":[74,120,142,148],"hybrid":[75,169],"statistical":[76,174],"knowledge-based":[78,104,177],"extraction":[80,155],"model,":[81,127],"able":[82],"extract":[84],"entities":[85],"relations":[87],"sentence":[90],"level.":[91],"model":[93],"attempts":[94],"retain":[96],"improve":[98],"high":[100],"accuracy":[101],"levels":[102],"systems":[105],"while":[106,179],"drastically":[107],"reducing":[108],"amount":[110,190],"manual":[112,185],"labor":[113],"by":[114,140],"relying":[115],"on":[116],"statistics":[117],"drawn":[118],"from":[119],"training":[121,158,192,206],"corpus.":[122,163],"implementation":[124],"called":[128],"TEG":[129],"(Trainable":[130],"Extraction":[131],"Grammar),":[132],"be":[134],"adapted":[135],"any":[137],"IE":[138],"domain":[139],"writing":[141,187],"suitable":[143,214],"set":[144],"rules":[146],"SCFG":[149],"(Stochastic":[150],"Context":[151],"Free":[152],"Grammar)":[153],"language,":[156],"them":[159],"using":[160],"annotated":[162],"experiments":[165],"show":[166],"our":[168,200],"approach":[170],"outperforms":[171],"both":[172],"purely":[173,176],"systems,":[178],"requiring":[180],"orders":[181],"magnitude":[183],"less":[184],"rule":[186],"smaller":[189],"data.":[193],"We":[194],"also":[195],"demonstrate":[196],"robustness":[198],"system":[201,212],"under":[202],"conditions":[203],"poor":[205],"data":[207],"quality.":[208],"makes":[210],"very":[213],"for":[215],"legacy":[217],"pages":[219],"pages.":[223]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}