{"id":"https://openalex.org/W2609330031","doi":"https://doi.org/10.1587/transinf.2016edp7375","title":"LTDE: A Layout Tree Based Approach for Deep Page Data Extraction","display_name":"LTDE: A Layout Tree Based Approach for Deep Page Data Extraction","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2609330031","doi":"https://doi.org/10.1587/transinf.2016edp7375","mag":"2609330031"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016edp7375","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2016edp7375","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7375/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7375/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024752776","display_name":"Jun Zeng","orcid":"https://orcid.org/0000-0003-3129-9052"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun ZENG","raw_affiliation_strings":["School of Software Engineering, Chongqing University","The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Chongqing University","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725575","display_name":"Li Feng","orcid":"https://orcid.org/0000-0002-6233-3463"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng LI","raw_affiliation_strings":["School of Software Engineering, Chongqing University","Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Chongqing University","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]},{"raw_affiliation_string":"The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025409280","display_name":"Brendan Flanagan","orcid":"https://orcid.org/0000-0001-7644-997X"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Brendan FLANAGAN","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University","The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006267512","display_name":"Sachio Hirokawa","orcid":"https://orcid.org/0000-0002-8050-1109"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]},{"id":"https://openalex.org/I202367325","display_name":"Oldenburger Institut f\u00fcr Informatik","ror":"https://ror.org/003sav189","country_code":"DE","type":"facility","lineage":["https://openalex.org/I202367325"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Sachio HIROKAWA","raw_affiliation_strings":["Research Institute for Information Technology, Kyushu University","Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan"],"affiliations":[{"raw_affiliation_string":"Research Institute for Information Technology, Kyushu University","institution_ids":["https://openalex.org/I135598925","https://openalex.org/I202367325"]},{"raw_affiliation_string":"Graduate School of Information Sci-ence and Electrical Engineering, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]},{"raw_affiliation_string":"The author is with Research Institute for Information Tech-nology, Kyushu University, Fukuoka-shi, 819-0395 Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024752776"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.5059,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72759384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E100.D","issue":"5","first_page":"1067","last_page":"1078"},"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":0.9587000012397766,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9570000171661377,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9087731838226318},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5348078012466431},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5064307451248169},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.46167609095573425},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46034693717956543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4470917880535126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4114457070827484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33057671785354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9087731838226318},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5348078012466431},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5064307451248169},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.46167609095573425},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46034693717956543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4470917880535126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4114457070827484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33057671785354614},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016edp7375","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2016edp7375","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7375/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016edp7375","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2016edp7375","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7375/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3841847876","display_name":null,"funder_award_id":"2015CDJXY","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5868786994","display_name":null,"funder_award_id":"cstc2013jcyjA1658","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6003087894","display_name":null,"funder_award_id":"61502062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6809183074","display_name":null,"funder_award_id":"Project No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8629150016","display_name":null,"funder_award_id":"cstc2014jcyjA40054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2609330031.pdf","grobid_xml":"https://content.openalex.org/works/W2609330031.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W88822615","https://openalex.org/W1616576116","https://openalex.org/W1803802947","https://openalex.org/W1927338256","https://openalex.org/W1973356180","https://openalex.org/W1976373002","https://openalex.org/W1999362186","https://openalex.org/W2015551056","https://openalex.org/W2018682463","https://openalex.org/W2037504378","https://openalex.org/W2053045757","https://openalex.org/W2057857570","https://openalex.org/W2065568440","https://openalex.org/W2084886972","https://openalex.org/W2087166835","https://openalex.org/W2100184871","https://openalex.org/W2101726980","https://openalex.org/W2106568316","https://openalex.org/W2114535528","https://openalex.org/W2128341918","https://openalex.org/W2133669904","https://openalex.org/W2134150392","https://openalex.org/W2135479443","https://openalex.org/W2136072238","https://openalex.org/W2142385501","https://openalex.org/W2145404631","https://openalex.org/W2148317291","https://openalex.org/W2157160236","https://openalex.org/W2160189941","https://openalex.org/W2171364811"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W2975617233","https://openalex.org/W2377877252","https://openalex.org/W2362914816","https://openalex.org/W2372644337"],"abstract_inverted_index":{"Content":[0],"extraction":[1,158],"from":[2,51],"deep":[3,53,72],"Web":[4,20,54,73,76,156],"pages":[5],"has":[6,130,149],"received":[7],"great":[8],"attention":[9],"in":[10,71,126],"recent":[11],"years.":[12],"However,":[13],"the":[14,28,34,59,65,91,110,123,127,131,137],"increasingly":[15],"complicated":[16],"HTML":[17,35,60],"structure":[18],"of":[19,57,68,84,117],"documents":[21],"makes":[22],"it":[23],"more":[24],"difficult":[25],"to":[26,47,108,140,160],"recognize":[27],"data":[29,49,69,88,138,157],"records":[30,50,70,89,139],"by":[31],"only":[32],"analyzing":[33,58],"source":[36,61],"code.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42,100],"a":[43,52,81,101],"method":[44,104],"named":[45,105],"LTDE":[46,63,148],"extract":[48],"page.":[55],"Instead":[56],"code,":[62],"utilizes":[64],"visual":[66,85,92,113,124],"features":[67],"pages.":[74],"A":[75],"page":[77],"is":[78,120],"considered":[79],"as":[80,136],"finite":[82],"set":[83],"blocks.":[86,114],"The":[87,115,143],"are":[90,134],"blocks":[93,125],"that":[94,129,147],"have":[95],"similar":[96,111],"layout.":[97],"We":[98],"also":[99],"pattern":[102],"recognizing":[103],"layout":[106,112],"tree":[107],"cluster":[109,128],"weight":[116,133],"all":[118],"clusters":[119],"calculated,":[121],"and":[122,152],"highest":[132],"chosen":[135],"be":[141],"extracted.":[142],"experiment":[144],"results":[145],"show":[146],"higher":[150],"effectiveness":[151],"better":[153],"robustness":[154],"for":[155],"compared":[159],"previous":[161],"works.":[162]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
