{"id":"https://openalex.org/W2559989503","doi":"https://doi.org/10.1016/j.ipm.2016.11.006","title":"Sampling strategies for information extraction over the deep web","display_name":"Sampling strategies for information extraction over the deep web","publication_year":2016,"publication_date":"2016-12-06","ids":{"openalex":"https://openalex.org/W2559989503","doi":"https://doi.org/10.1016/j.ipm.2016.11.006","mag":"2559989503"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2016.11.006","pdf_url":"https://www.sciencedirect.com/science/article/am/pii/S0306457316306318","source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.sciencedirect.com/science/article/am/pii/S0306457316306318","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074134679","display_name":"Pablo Barrio","orcid":"https://orcid.org/0000-0002-4410-0682"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"funder","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pablo Barrio","raw_affiliation_strings":["Columbia University, Computer Science Department, 500 West 120th Street, Room 405, MC0401, New York, NY 10027, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, Computer Science Department, 500 West 120th Street, Room 405, MC0401, New York, NY 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"funder","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Columbia University, Computer Science Department, 500 West 120th Street, Room 405, MC0401, New York, NY 10027, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, Computer Science Department, 500 West 120th Street, Room 405, MC0401, New York, NY 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074134679"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":null,"fwci":5.007,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":14,"citation_normalized_percentile":{"value":0.931191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":89},"biblio":{"volume":"53","issue":"2","first_page":"309","last_page":"331"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9999,"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":0.9999,"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/T11478","display_name":"Caching and Content Delivery","score":0.9897,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9892,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89802337},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7421806},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6019261},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.57054937},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5693874},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.53925216},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49555767},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47307596},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4151408},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3656865},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.093161345},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2016.11.006","pdf_url":"https://www.sciencedirect.com/science/article/am/pii/S0306457316306318","source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2016.11.006","pdf_url":"https://www.sciencedirect.com/science/article/am/pii/S0306457316306318","source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.63}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"IIS-08-11038"},{"funder":"https://openalex.org/F4320306116","funder_display_name":"U.S. Department of the Interior","award_id":"D11PC20153"}],"datasets":[],"versions":[],"referenced_works_count":61,"referenced_works":["https://openalex.org/W1434647451","https://openalex.org/W1489992655","https://openalex.org/W1493270114","https://openalex.org/W1586176254","https://openalex.org/W1670263352","https://openalex.org/W1934019294","https://openalex.org/W1965555277","https://openalex.org/W1967932772","https://openalex.org/W1975048439","https://openalex.org/W1986828474","https://openalex.org/W1989856433","https://openalex.org/W1998698985","https://openalex.org/W2004087619","https://openalex.org/W2014016001","https://openalex.org/W2024490588","https://openalex.org/W2026289298","https://openalex.org/W2027746662","https://openalex.org/W2029685080","https://openalex.org/W2031648200","https://openalex.org/W2038522479","https://openalex.org/W2043499927","https://openalex.org/W2045463753","https://openalex.org/W2078278619","https://openalex.org/W2081948558","https://openalex.org/W2090765848","https://openalex.org/W2094930182","https://openalex.org/W2095007791","https://openalex.org/W2096891167","https://openalex.org/W2102942431","https://openalex.org/W2103333826","https://openalex.org/W2116341550","https://openalex.org/W2116780029","https://openalex.org/W2118165382","https://openalex.org/W2118356300","https://openalex.org/W2121315872","https://openalex.org/W2124673015","https://openalex.org/W2125969310","https://openalex.org/W2129214100","https://openalex.org/W2140390894","https://openalex.org/W2141099517","https://openalex.org/W2151007976","https://openalex.org/W2155341658","https://openalex.org/W2155737120","https://openalex.org/W2163362093","https://openalex.org/W2164135737","https://openalex.org/W2168561231","https://openalex.org/W2170108941","https://openalex.org/W2170188121","https://openalex.org/W2170971772","https://openalex.org/W223119678","https://openalex.org/W2244776650","https://openalex.org/W2278404975","https://openalex.org/W2294284203","https://openalex.org/W2306028628","https://openalex.org/W2309755354","https://openalex.org/W2399179762","https://openalex.org/W2799873608","https://openalex.org/W2911388033","https://openalex.org/W2963639300","https://openalex.org/W3041351009","https://openalex.org/W4285579224"],"related_works":["https://openalex.org/W9598337","https://openalex.org/W8432713","https://openalex.org/W8129070","https://openalex.org/W7293280","https://openalex.org/W6984603","https://openalex.org/W4391872","https://openalex.org/W3148594","https://openalex.org/W2605135","https://openalex.org/W1250848","https://openalex.org/W10954916"],"abstract_inverted_index":null,"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2559989503","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-03-21T16:35:34.003774","created_date":"2016-12-16"}