{"id":"https://openalex.org/W2584049620","doi":"https://doi.org/10.1145/3018661.3018740","title":"Synthesis of Forgiving Data Extractors","display_name":"Synthesis of Forgiving Data Extractors","publication_year":2017,"publication_date":"2017-02-02","ids":{"openalex":"https://openalex.org/W2584049620","doi":"https://doi.org/10.1145/3018661.3018740","mag":"2584049620"},"language":"en","primary_location":{"id":"doi:10.1145/3018661.3018740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3018661.3018740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM International Conference on Web Search and Data Mining","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/A5081736887","display_name":"Adi Omari","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Adi Omari","raw_affiliation_strings":["Technion, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102884448","display_name":"Sharon Shoham","orcid":"https://orcid.org/0000-0002-7226-3526"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Shoham","raw_affiliation_strings":["Tel Aviv University, Tel Aviv , Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv , Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061044883","display_name":"Eran Yahav","orcid":"https://orcid.org/0000-0003-4305-6314"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eran Yahav","raw_affiliation_strings":["Technion, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081736887"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":3.869,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94147283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"394"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9954000115394592,"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.7963089942932129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.738246738910675},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7308989763259888},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4768472909927368},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.43485382199287415},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42054638266563416},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3565788269042969},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12849631905555725}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7963089942932129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738246738910675},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7308989763259888},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4768472909927368},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.43485382199287415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42054638266563416},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3565788269042969},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12849631905555725},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3018661.3018740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3018661.3018740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524234997","https://openalex.org/W1553019137","https://openalex.org/W1912123407","https://openalex.org/W1975255945","https://openalex.org/W2002956097","https://openalex.org/W2015551056","https://openalex.org/W2036383017","https://openalex.org/W2040757233","https://openalex.org/W2041247992","https://openalex.org/W2056112725","https://openalex.org/W2069388662","https://openalex.org/W2080132606","https://openalex.org/W2106568316","https://openalex.org/W2116471642","https://openalex.org/W2121751007","https://openalex.org/W2125055259","https://openalex.org/W2129595335","https://openalex.org/W2133990480","https://openalex.org/W2135479443","https://openalex.org/W2143309843","https://openalex.org/W2149706766","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2161861392","https://openalex.org/W2230980198","https://openalex.org/W2356873185","https://openalex.org/W2364692302","https://openalex.org/W2465169987","https://openalex.org/W4236137412"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2080135837","https://openalex.org/W2793679056","https://openalex.org/W3145050838","https://openalex.org/W4283332091","https://openalex.org/W2393154870","https://openalex.org/W4237873526"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,16],"problem":[3,22],"of":[4,12,19],"synthesizing":[5],"a":[6,10,40],"robust":[7],"data-extractor":[8],"from":[9,30],"family":[11],"websites":[13],"that":[14],"contain":[15],"same":[17],"kind":[18],"information.":[20],"This":[21],"is":[23],"common":[24],"when":[25,36],"trying":[26],"to":[27],"aggregate":[28],"information":[29,38],"many":[31],"web":[32],"sites,":[33],"for":[34,39],"example,":[35],"extracting":[37],"price-comparison":[41],"site.":[42]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}