{"id":"https://openalex.org/W1971125461","doi":"https://doi.org/10.1145/2063576.2063713","title":"Semi-supervised multi-task learning of structured prediction models for web information extraction","display_name":"Semi-supervised multi-task learning of structured prediction models for web information extraction","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W1971125461","doi":"https://doi.org/10.1145/2063576.2063713","mag":"1971125461"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063713","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/A5063223563","display_name":"Paramveer S. Dhillon","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paramveer S. Dhillon","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111436183","display_name":"Sundararajan Sellamanickam","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sundararajan Sellamanickam","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109041839","display_name":"Sathiya Keerthi Selvaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sathiya Keerthi Selvaraj","raw_affiliation_strings":["Yahoo! Labs, Santa Clara, CA, USA","Yahoo! Labs., Santa Clara, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Santa Clara, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063223563"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.7644,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82231803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"957","last_page":"966"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973000288009644,"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":0.9916999936103821,"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":0.7887395620346069},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7035049200057983},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5907275676727295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5892044901847839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5403028726577759},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5338977575302124},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5177428126335144},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5169610381126404},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45664307475090027},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.45262664556503296},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4482019543647766},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36270177364349365},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15847653150558472},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12500661611557007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09853518009185791},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08808693289756775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887395620346069},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7035049200057983},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5907275676727295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5892044901847839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403028726577759},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5338977575302124},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5177428126335144},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5169610381126404},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45664307475090027},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.45262664556503296},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4482019543647766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36270177364349365},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15847653150558472},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12500661611557007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09853518009185791},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08808693289756775},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2063576.2063713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063713","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.2145","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.2145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.keerthis.com/cikm116-dhillon.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.9638","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.9638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.seas.upenn.edu/~pasingh/cikm116-dhillon.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W197443874","https://openalex.org/W236085609","https://openalex.org/W1494141893","https://openalex.org/W1521051295","https://openalex.org/W1534730506","https://openalex.org/W1553019137","https://openalex.org/W1595917421","https://openalex.org/W1599188306","https://openalex.org/W1616576116","https://openalex.org/W1709989312","https://openalex.org/W1908728294","https://openalex.org/W1966000522","https://openalex.org/W1973483159","https://openalex.org/W1992994083","https://openalex.org/W2002806284","https://openalex.org/W2019577381","https://openalex.org/W2029873015","https://openalex.org/W2069057437","https://openalex.org/W2079594573","https://openalex.org/W2092827762","https://openalex.org/W2095758845","https://openalex.org/W2102166778","https://openalex.org/W2104086170","https://openalex.org/W2108126629","https://openalex.org/W2123827533","https://openalex.org/W2124410446","https://openalex.org/W2130903752","https://openalex.org/W2134150392","https://openalex.org/W2143104527","https://openalex.org/W2143309843","https://openalex.org/W2144752499","https://openalex.org/W2145007893","https://openalex.org/W2147880316","https://openalex.org/W2148252020","https://openalex.org/W2150969560","https://openalex.org/W2153959628","https://openalex.org/W2154326713","https://openalex.org/W2159874616","https://openalex.org/W2171364811","https://openalex.org/W2913340405","https://openalex.org/W2913389685"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Extracting":[0],"information":[1],"from":[2,204],"web":[3],"pages":[4],"is":[5,49,181,218],"an":[6],"important":[7,40],"problem;":[8],"it":[9,91,217],"has":[10,87],"several":[11,88,234],"applications":[12],"such":[13],"as":[14,145,165],"providing":[15],"improved":[16],"search":[17],"results":[18,238],"and":[19,58,103,201,207,250],"construction":[20],"of":[21,42,56,108,121,137,155,230],"databases":[22],"to":[23,37,96,116,220],"serve":[24],"user":[25],"queries.":[26],"In":[27],"this":[28,74,125],"paper":[29],"we":[30,76,148],"propose":[31,77],"a":[32,53,60,78,122,128,139,146,153,166,189,193,211,222,254],"novel":[33],"structured":[34],"prediction":[35],"method":[36,86,126,160,180,232],"address":[38,97,117],"two":[39,185],"aspects":[41],"the":[43,98,106,118,135,150,174,178,228],"extraction":[44],"problem:":[45],"(1)":[46,187],"labeled":[47,100,200],"data":[48,95,101,203],"available":[50],"only":[51,214],"for":[52,131,142,152,192,210],"small":[54],"number":[55],"sites":[57,156],"(2)":[59,208],"machine":[61],"learned":[62],"global":[63,123],"model":[64,130,141,191],"does":[65],"not":[66],"generalize":[67],"adequately":[68],"well":[69],"across":[70],"many":[71],"websites.":[72],"For":[73],"purpose,":[75],"weight":[79],"space":[80],"based":[81,111,169],"graph":[82,109,167],"regularization":[83,110,168],"method.":[84],"This":[85],"advantages.":[89],"First,":[90],"can":[92,161,195,244],"use":[93],"unlabeled":[94,202,215],"limited":[99],"problem":[102,136],"falls":[104],"in":[105,184,253],"class":[107],"semi-supervised":[112,249],"learning":[113,171,188,252],"approaches.":[114],"Second,":[115],"generalization":[119],"inadequacy":[120],"model,":[124],"builds":[127],"local":[129,140,190,224],"each":[132,143],"website.":[133],"Viewing":[134],"building":[138],"website":[144,194,212],"task,":[147],"learn":[149,221],"models":[151,175],"collection":[154],"jointly;":[157],"thus":[158],"our":[159,231],"also":[162],"be":[163,196,245],"seen":[164],"multi-task":[170,251],"approach.":[172],"Learning":[173],"jointly":[176],"with":[177,213],"proposed":[179],"very":[182],"useful":[183],"ways:":[186],"effectively":[197],"influenced":[198],"by":[199,247],"other":[205],"websites;":[206],"even":[209],"examples":[216],"possible":[219],"decent":[223],"model.":[225],"We":[226],"demonstrate":[227],"efficacy":[229],"on":[233],"real-life":[235],"data;":[236],"experimental":[237],"show":[239],"that":[240],"significant":[241],"performance":[242],"improvement":[243],"obtained":[246],"combining":[248],"single":[255],"framework.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}