{"id":"https://openalex.org/W2142385501","doi":"https://doi.org/10.1145/2063576.2063761","title":"Towards a unified solution","display_name":"Towards a unified solution","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2142385501","doi":"https://doi.org/10.1145/2063576.2063761","mag":"2142385501"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","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/A5086674741","display_name":"Lidong Bing","orcid":"https://orcid.org/0000-0003-4565-6313"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lidong Bing","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Lam","orcid":"https://orcid.org/0000-0001-5479-377X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062459637","display_name":"Yuan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Gu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086674741"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":6.6505,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96475166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1265","last_page":"1274"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9879999756813049,"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/T11478","display_name":"Caching and Content Delivery","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8438061475753784},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6449810266494751},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6363535523414612},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5542371869087219},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5230456590652466},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5175322890281677},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5166192650794983},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4999110698699951},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48781898617744446},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4783708155155182},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4599562883377075},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.45572370290756226},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4152371287345886},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.41240790486335754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36934906244277954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32804450392723083},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.250380277633667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2340095043182373},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09954822063446045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438061475753784},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6449810266494751},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6363535523414612},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5542371869087219},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5230456590652466},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5175322890281677},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5166192650794983},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4999110698699951},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48781898617744446},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4783708155155182},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4599562883377075},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.45572370290756226},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4152371287345886},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.41240790486335754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36934906244277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32804450392723083},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.250380277633667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2340095043182373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09954822063446045},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1616576116","https://openalex.org/W1927338256","https://openalex.org/W1967382114","https://openalex.org/W1973483159","https://openalex.org/W2015551056","https://openalex.org/W2023094000","https://openalex.org/W2027864253","https://openalex.org/W2035302703","https://openalex.org/W2065568440","https://openalex.org/W2067416210","https://openalex.org/W2069388662","https://openalex.org/W2072936489","https://openalex.org/W2096806473","https://openalex.org/W2102189859","https://openalex.org/W2104086170","https://openalex.org/W2119577990","https://openalex.org/W2121751007","https://openalex.org/W2128341918","https://openalex.org/W2128836931","https://openalex.org/W2131150402","https://openalex.org/W2133669904","https://openalex.org/W2135479443","https://openalex.org/W2138405339","https://openalex.org/W2140327372","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2157160236","https://openalex.org/W2160189941","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2168358004","https://openalex.org/W2171364811","https://openalex.org/W3006373977","https://openalex.org/W4233527139","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2389117260","https://openalex.org/W1510682440","https://openalex.org/W4313343427","https://openalex.org/W1998610287","https://openalex.org/W2014706981","https://openalex.org/W2364496167","https://openalex.org/W2144340991","https://openalex.org/W3034799230","https://openalex.org/W2142385501","https://openalex.org/W1966278314"],"abstract_inverted_index":{"Although":[0],"the":[1,69,76,116,120,150],"task":[2,40],"of":[3,85,125],"data":[4,104,159],"record":[5,105],"extraction":[6],"from":[7,92,115],"Web":[8,81],"pages":[9,20],"has":[10],"been":[11],"studied":[12],"extensively,":[13],"yet":[14],"it":[15,97],"fails":[16],"to":[17,22,37,74],"handle":[18,100],"many":[19],"due":[21],"their":[23],"complexity":[24],"in":[25,46,78,149],"format":[26],"or":[27,130],"layout.":[28],"In":[29],"this":[30,39],"paper,":[31],"we":[32,134],"propose":[33,135],"a":[34,47,79,136,146],"unified":[35],"method":[36,87,173],"tackle":[38],"by":[41,110],"addressing":[42],"several":[43,63],"key":[44],"issues":[45],"uniform":[48],"manner.":[49],"A":[50],"new":[51],"search":[52,65,121],"structure,":[53],"named":[54],"as":[55,145],"Record":[56],"Segmentation":[57],"Tree":[58],"(RST),":[59],"is":[60,89,95,108],"designed,":[61],"and":[62,102,164],"efficient":[64],"pruning":[66],"strategies":[67],"on":[68,157],"RST":[70,117],"structure":[71,118],"are":[72,155],"proposed":[73],"identify":[75],"records":[77],"given":[80],"page.":[82],"Another":[83],"characteristic":[84],"our":[86,172],"which":[88,140],"significantly":[90],"different":[91],"previous":[93],"works":[94],"that":[96,171],"can":[98],"effectively":[99],"complicated":[101],"challenging":[103],"regions.":[106],"It":[107],"achieved":[109],"generating":[111],"subtree":[112],"groups":[113],"dynamically":[114],"during":[119],"process.":[122],"Furthermore,":[123],"instead":[124],"using":[126],"string":[127],"edit":[128,132,138],"distance":[129,139],"tree":[131],"distance,":[133],"token-based":[137],"takes":[141],"each":[142],"DOM":[143],"node":[144],"basic":[147],"unit":[148],"cost":[151],"calculation.":[152],"Extensive":[153],"experiments":[154],"conducted":[156],"four":[158],"sets,":[160],"including":[161],"flat,":[162],"nested,":[163],"intertwine":[165],"records.":[166],"The":[167],"experimental":[168],"results":[169],"demonstrate":[170],"achieves":[174],"higher":[175],"accuracy":[176],"compared":[177],"with":[178],"three":[179],"state-of-the-art":[180],"methods.":[181]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}