{"id":"https://openalex.org/W2973997559","doi":"https://doi.org/10.1145/3342558.3345391","title":"Predictable and Consistent Information Extraction","display_name":"Predictable and Consistent Information Extraction","publication_year":2019,"publication_date":"2019-09-19","ids":{"openalex":"https://openalex.org/W2973997559","doi":"https://doi.org/10.1145/3342558.3345391","mag":"2973997559"},"language":"en","primary_location":{"id":"doi:10.1145/3342558.3345391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3342558.3345391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3342558.3345391","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3342558.3345391","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087611357","display_name":"Besat Kassaie","orcid":"https://orcid.org/0009-0007-6924-6884"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Besat Kassaie","raw_affiliation_strings":["Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000681085","display_name":"Frank Wm. Tompa","orcid":"https://orcid.org/0000-0002-1907-9535"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Frank Wm. Tompa","raw_affiliation_strings":["Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087611357"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.882,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88113831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8264342546463013},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7271448373794556},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7145826816558838},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5886958837509155},{"id":"https://openalex.org/keywords/source-document","display_name":"Source document","score":0.551243007183075},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.5071310997009277},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.4711902141571045},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.45657989382743835},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4288497567176819},{"id":"https://openalex.org/keywords/information-source","display_name":"Information source (mathematics)","score":0.4108569324016571},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3373233675956726},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07682618498802185},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06541827321052551},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06400680541992188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264342546463013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7271448373794556},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7145826816558838},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5886958837509155},{"id":"https://openalex.org/C105888452","wikidata":"https://www.wikidata.org/wiki/Q7565148","display_name":"Source document","level":2,"score":0.551243007183075},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.5071310997009277},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.4711902141571045},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.45657989382743835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4288497567176819},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.4108569324016571},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3373233675956726},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07682618498802185},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06541827321052551},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06400680541992188},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342558.3345391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3342558.3345391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3342558.3345391","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3342558.3345391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3342558.3345391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3342558.3345391","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320322676","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973997559.pdf","grobid_xml":"https://content.openalex.org/works/W2973997559.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1552694902","https://openalex.org/W1975937116","https://openalex.org/W1999563429","https://openalex.org/W2060916782","https://openalex.org/W2068882115","https://openalex.org/W2114998795","https://openalex.org/W2146143659","https://openalex.org/W2157317150","https://openalex.org/W2167541073","https://openalex.org/W2245160765","https://openalex.org/W2913389685","https://openalex.org/W2966211635"],"related_works":["https://openalex.org/W2911277629","https://openalex.org/W3047661136","https://openalex.org/W2059987156","https://openalex.org/W4237258125","https://openalex.org/W2317798554","https://openalex.org/W1728604218","https://openalex.org/W2120284164","https://openalex.org/W2379201243","https://openalex.org/W3101321521","https://openalex.org/W3034456347"],"abstract_inverted_index":{"Information":[0],"extraction":[1],"programs":[2],"(extractors)":[3],"can":[4],"be":[5,38,57],"applied":[6],"to":[7,9,18,23,37,76,80],"documents":[8,63],"isolate":[10],"structured":[11],"versions":[12],"of":[13,48],"some":[14],"content,":[15],"that":[16,78],"is,":[17],"create":[19],"tabular":[20],"records":[21],"corresponding":[22],"facts":[24],"found":[25],"in":[26,32,86],"the":[27,30,51,60,65],"documents.":[28,89],"If":[29],"data":[31,49],"an":[33],"extracted":[34,81],"table":[35],"needs":[36],"updated":[39],"for":[40,68],"any":[41],"reason":[42],"(for":[43],"example,":[44],"as":[45],"a":[46],"result":[47],"cleaning),":[50],"source":[52,88],"document":[53],"will":[54],"no":[55],"longer":[56],"synchronized":[58],"with":[59],"data.":[61],"But":[62],"are":[64,83],"principal":[66],"medium":[67],"sharing":[69],"information":[70],"among":[71],"humans.":[72],"We":[73],"therefore":[74],"wish":[75],"ensure":[77],"changes":[79],"tables":[82],"reflected":[84],"correctly":[85],"their":[87]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
