{"id":"https://openalex.org/W2049936955","doi":"https://doi.org/10.1142/s0219427902000492","title":"Learning mDTD Extraction Patterns for Semi-structured Web Information Extraction","display_name":"Learning mDTD Extraction Patterns for Semi-structured Web Information Extraction","publication_year":2002,"publication_date":"2002-03-01","ids":{"openalex":"https://openalex.org/W2049936955","doi":"https://doi.org/10.1142/s0219427902000492","mag":"2049936955"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427902000492","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427902000492","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","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/A5100745975","display_name":"Dongseok Kim","orcid":"https://orcid.org/0000-0002-9876-3393"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"DONGSEOK KIM","raw_affiliation_strings":["Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109869190","display_name":"Jeong-Won Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"JEONGWON CHA","raw_affiliation_strings":["Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045508648","display_name":"Gary Geunbae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"GARY GEUNBAE LEE","raw_affiliation_strings":["Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, KoreaVisiting Researcher, CSLI, Stanford University","Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, KoreaVisiting Researcher, CSLI, Stanford University","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science & Engineering,  Pohang University of Science & Technology, San31, Hyoja, Pohang,  790-784, Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100745975"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.6633,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81642127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"01","first_page":"63","last_page":"78"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9855999946594238,"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":0.9837999939918518,"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":0.9102556705474854},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6212974786758423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5988649129867554},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.58690345287323},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5697304010391235},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.511454701423645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49886059761047363},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.48837393522262573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4563889503479004},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4535471200942993},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09144577383995056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9102556705474854},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6212974786758423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5988649129867554},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.58690345287323},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5697304010391235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.511454701423645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49886059761047363},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.48837393522262573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4563889503479004},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4535471200942993},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09144577383995056},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0219427902000492","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427902000492","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1999138184","https://openalex.org/W2126185232","https://openalex.org/W2136000097","https://openalex.org/W2162340487"],"related_works":["https://openalex.org/W2126185232","https://openalex.org/W2352298027","https://openalex.org/W4319940250","https://openalex.org/W842810586","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W2090814745","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W2169232658"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,8,98,153],"new":[4,135],"extraction":[5,73,100,176],"pattern,":[6],"called":[7],"modified":[9],"Document":[10],"Type":[11],"Definition":[12],"(mDTD),":[13],"which":[14,35,110],"relies":[15],"on":[16,118,141,165],"an":[17,45],"analytical":[18],"interpretation":[19],"method":[20],"to":[21,61,81,128],"identify":[22],"textual":[23],"fragments":[24],"of":[25,78],"documents":[26,117,164],"from":[27,37,109,115],"the":[28,38,55,59,63,119,142,147],"Web.":[29,120],"We":[30,159],"make":[31],"two":[32],"major":[33,83],"modifications":[34],"differ":[36],"conventional":[39],"DTD.":[40],"Regarding":[41],"syntax,":[42],"we":[43,57],"introduced":[44],"extended":[46],"content":[47],"model":[48],"with":[49,85,92,161],"more":[50],"operators":[51],"and":[52,72,146,167],"keywords.":[53],"For":[54,151],"semantics,":[56],"changed":[58],"way":[60],"interpret":[62],"mDTD":[64,67,79,105,131,136],"rules.":[65],"The":[66,75,102,171],"can":[68],"represent":[69],"HTML":[70],"structures":[71],"targets.":[74],"design":[76],"goal":[77],"is":[80,156],"overcome":[82],"barriers":[84],"information":[86],"extraction,":[87],"such":[88],"as":[89,106,126],"domain":[90],"portability":[91],"minimum":[93],"human":[94],"intervention":[95],"while":[96],"maintaining":[97],"high":[99],"performance.":[101],"user":[103],"composes":[104],"seed":[107],"rules":[108,137],"our":[111],"system":[112],"extracts":[113],"instances":[114,123],"structured":[116],"These":[121],"extracted":[122],"are":[124,139],"used":[125],"inputs":[127],"SmL":[129,133],"(Sequential":[130],"Learner).":[132],"generates":[134],"that":[138],"based":[140],"part-of-speech":[143],"(POS)":[144],"tag":[145],"lexical":[148],"similarity":[149],"features.":[150],"learning,":[152],"hand-tagged":[154],"corpus":[155],"not":[157],"required.":[158],"experimented":[160],"200":[162],"Web":[163],"audio":[166],"video":[168],"shopping":[169],"sites.":[170],"results":[172],"show":[173],"91.3%":[174],"average":[175],"precision.":[177]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}