{"id":"https://openalex.org/W2145600026","doi":"https://doi.org/10.1145/2396761.2398464","title":"A simple approach to the design of site-level extractors using domain-centric principles","display_name":"A simple approach to the design of site-level extractors using domain-centric principles","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2145600026","doi":"https://doi.org/10.1145/2396761.2398464","mag":"2145600026"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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/A5035825042","display_name":"Chong Long","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":true,"raw_author_name":"Chong Long","raw_affiliation_strings":["Yahoo!, Beijing, China","Yahoo!, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Yahoo!, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"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":"Xiubo Geng","raw_affiliation_strings":["Yahoo!, Beijing, China","Yahoo!, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Yahoo!, Beijing, China#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653276","display_name":"Xu Chang","orcid":"https://orcid.org/0000-0003-3672-5380"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109221570","display_name":"Sathiya Keerthi","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sathiya Keerthi","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","Microsoft Redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035825042"],"corresponding_institution_ids":["https://openalex.org/I1325784139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.19798287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1517","last_page":"1521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9975000023841858,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9872999787330627,"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":0.7987794280052185},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7640807628631592},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7624936699867249},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.715274453163147},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6713460087776184},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.6315381526947021},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49492186307907104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4306989014148712},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.350005567073822},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3467384874820709},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32955795526504517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16210612654685974},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05531668663024902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987794280052185},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7640807628631592},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7624936699867249},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.715274453163147},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6713460087776184},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.6315381526947021},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49492186307907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4306989014148712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.350005567073822},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3467384874820709},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32955795526504517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16210612654685974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05531668663024902},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2396761.2398464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.4393","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.4393","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/sp158-long.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1521051295","https://openalex.org/W1973483159","https://openalex.org/W2070090726","https://openalex.org/W2080132606","https://openalex.org/W2137216273","https://openalex.org/W2154445423","https://openalex.org/W2160218441","https://openalex.org/W2913389685"],"related_works":["https://openalex.org/W2368019753","https://openalex.org/W2333930193","https://openalex.org/W2737356002","https://openalex.org/W2246241526","https://openalex.org/W4301122218","https://openalex.org/W2374150061","https://openalex.org/W2081340182","https://openalex.org/W4210711561","https://openalex.org/W78216654","https://openalex.org/W2478607759"],"abstract_inverted_index":{"We":[0,36],"consider":[1],"the":[2,58,77,124],"problem":[3,29],"of":[4,13,19,73,79,107,144],"extracting,":[5],"in":[6,82,93,120,142],"a":[7,10,16,38,48,51,66,70,104,111],"domain-centric":[8],"fashion,":[9],"given":[11],"set":[12,68,106],"attributes":[14,113,118],"from":[15,69],"large":[17],"number":[18,72,78],"semi-structured":[20],"websites.":[21],"Previous":[22],"approaches":[23],"[7,":[24],"5]":[25],"to":[26,102,123],"solve":[27],"this":[28],"are":[30],"based":[31],"on":[32,128],"page":[33],"level":[34,60],"inference.":[35],"propose":[37],"distinct":[39],"new":[40],"approach":[41,138],"that":[42,54,91,136],"directly":[43],"chooses":[44],"attribute":[45],"extractors":[46,81,109],"for":[47,110],"site":[49,84],"using":[50,65],"scoring":[52],"mechanism":[53],"is":[55,139],"designed":[56],"at":[57],"domain":[59],"via":[61],"simple":[62],"classification":[63],"methods":[64],"training":[67],"small":[71,86,105],"sites.":[74],"To":[75],"keep":[76],"candidate":[80,108],"each":[83],"manageably":[85],"we":[87],"use":[88],"two":[89],"observations":[90],"hold":[92],"most":[94],"domains:":[95],"(a)":[96],"imprecise":[97],"annotators":[98],"can":[99],"be":[100],"used":[101],"identify":[103],"few":[112],"(anchors);":[114],"and":[115,133],"(b)":[116],"non-anchor":[117],"lie":[119],"close":[121],"proximity":[122],"anchor":[125],"attributes.":[126],"Experiments":[127],"three":[129],"domains":[130],"(Events,":[131],"Books":[132],"Restaurants)":[134],"show":[135],"our":[137],"very":[140],"effective":[141],"spite":[143],"its":[145],"simplicity.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}