{"id":"https://openalex.org/W4367046663","doi":"https://doi.org/10.1145/3543507.3583387","title":"Learning Structural Co-occurrences for Structured Web Data Extraction in Low-Resource Settings","display_name":"Learning Structural Co-occurrences for Structured Web Data Extraction in Low-Resource Settings","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367046663","doi":"https://doi.org/10.1145/3543507.3583387"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583387","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583387","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100389535","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-5936-6678"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604886","display_name":"Bowen Yu","orcid":"https://orcid.org/0000-0002-6804-1859"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Yu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080686378","display_name":"Tingwen Liu","orcid":"https://orcid.org/0000-0002-0750-6923"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingwen Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090078778","display_name":"Tianyun Liu","orcid":"https://orcid.org/0000-0003-3213-9077"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyun Liu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038842107","display_name":"Yubin Wang","orcid":"https://orcid.org/0000-0002-6464-3203"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubin Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083561214","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-2529-7643"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Guo","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100389535"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.265,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89826841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1683","last_page":"1692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9796000123023987,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9718999862670898,"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":0.8201279640197754},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6643410325050354},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.623062014579773},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5881323218345642},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5662021636962891},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5394798517227173},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5287936329841614},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4865940809249878},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47217363119125366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.443167120218277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3767229914665222},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37003087997436523},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34444668889045715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201279640197754},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6643410325050354},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.623062014579773},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5881323218345642},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5662021636962891},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5394798517227173},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5287936329841614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4865940809249878},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47217363119125366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.443167120218277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767229914665222},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37003087997436523},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34444668889045715},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543507.3583387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583387","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543507.3583387","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G4257157713","display_name":null,"funder_award_id":"No.2021YFB3100600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4302849700","display_name":null,"funder_award_id":"2021YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8151936980","display_name":null,"funder_award_id":"2021YFB3100600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8817924637","display_name":null,"funder_award_id":"XDC02040400","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G969280182","display_name":null,"funder_award_id":"2021153","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367046663.pdf","grobid_xml":"https://content.openalex.org/works/W4367046663.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1795600436","https://openalex.org/W1973483159","https://openalex.org/W2080132606","https://openalex.org/W2090243146","https://openalex.org/W2117372041","https://openalex.org/W2121751007","https://openalex.org/W2161861392","https://openalex.org/W2163072729","https://openalex.org/W2166817967","https://openalex.org/W2167138081","https://openalex.org/W2799010330","https://openalex.org/W2890881297","https://openalex.org/W2914479823","https://openalex.org/W2949694638","https://openalex.org/W2953356739","https://openalex.org/W2963687836","https://openalex.org/W2979826702","https://openalex.org/W2996913633","https://openalex.org/W2998385486","https://openalex.org/W3011809564","https://openalex.org/W3035153870","https://openalex.org/W3081176230","https://openalex.org/W3086232317","https://openalex.org/W3087714553","https://openalex.org/W3099461227","https://openalex.org/W3100117936","https://openalex.org/W3106445281","https://openalex.org/W3132781388","https://openalex.org/W3153917096","https://openalex.org/W3168656614","https://openalex.org/W3183859557","https://openalex.org/W3197688135","https://openalex.org/W3200209027","https://openalex.org/W3206324399","https://openalex.org/W3207577858","https://openalex.org/W4205326975","https://openalex.org/W4213039371","https://openalex.org/W4221167659"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2998827288","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W2185387300","https://openalex.org/W1544491176"],"abstract_inverted_index":{"Extracting":[0],"structured":[1],"information":[2],"from":[3],"all":[4],"manner":[5],"of":[6,26,50,80,190,198,201],"webpages":[7,79],"is":[8,67],"an":[9],"important":[10],"problem":[11],"with":[12],"the":[13,24,43,47,55,81,84,88,93,98,121,138,141,168,177,188,191,196],"potential":[14],"to":[15,34,45,118,161],"automate":[16],"many":[17],"real-world":[18],"applications.":[19],"Recent":[20],"work":[21],"has":[22],"shown":[23],"effectiveness":[25,60],"leveraging":[27],"DOM":[28,89,99,125],"trees":[29],"and":[30,36,52,97,127,147,157,183],"pre-trained":[31,131],"language":[32,132],"models":[33,179],"describe":[35],"encode":[37],"webpages.":[38],"However,":[39],"they":[40],"typically":[41],"optimize":[42],"model":[44,139,194],"learn":[46,140],"semantic":[48,95],"co-occurrence":[49],"elements":[51],"labels":[53],"in":[54,77,87,101,180,195],"same":[56,82,85,94],"webpage,":[57],"thus":[58],"their":[59],"depends":[61],"on":[62,167],"sufficient":[63],"labeled":[64],"data,":[65],"which":[66],"labor-intensive.":[68],"In":[69],"this":[70,102],"paper,":[71],"we":[72,112,148],"further":[73],"observe":[74],"structural":[75,122,135],"co-occurrences":[76,123,136],"different":[78],"website:":[83],"position":[86,103],"tree":[90,126],"usually":[91],"plays":[92],"role,":[96],"nodes":[100],"also":[104],"share":[105],"similar":[106],"surface":[107,128],"forms.":[108],"Motivated":[109],"by":[110],"this,":[111],"propose":[113],"a":[114],"novel":[115],"method,":[116],"Structor,":[117],"effectively":[119],"incorporate":[120],"over":[124],"form":[129],"into":[130],"models.":[133],"Such":[134],"help":[137],"task":[142],"better":[143],"under":[144],"low-resource":[145,155,159],"settings,":[146,182],"study":[149],"two":[150],"challenging":[151],"experimental":[152],"scenarios:":[153],"website-level":[154],"setting":[156],"webpage-level":[158],"setting,":[160],"evaluate":[162],"our":[163],"approach.":[164],"Extensive":[165],"experiments":[166],"public":[169],"SWDE":[170],"dataset":[171],"show":[172],"that":[173],"Structor":[174],"significantly":[175],"outperforms":[176],"state-of-the-art":[178],"both":[181],"even":[184],"achieves":[185],"three":[186],"times":[187],"performance":[189],"strong":[192],"baseline":[193],"case":[197],"extreme":[199],"lack":[200],"training":[202],"data.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
