{"id":"https://openalex.org/W2035266017","doi":"https://doi.org/10.1109/icde.2008.4497502","title":"An Algebraic Approach to Rule-Based Information Extraction","display_name":"An Algebraic Approach to Rule-Based Information Extraction","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2035266017","doi":"https://doi.org/10.1109/icde.2008.4497502","mag":"2035266017"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2008.4497502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","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/A5074416632","display_name":"Frederick Reiss","orcid":"https://orcid.org/0009-0002-1254-1798"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Frederick Reiss","raw_affiliation_strings":["Almaden Research Center, IBM, San Jose, CA, USA","[Almaden Res. Center, IBM, San Jose, CA]"],"affiliations":[{"raw_affiliation_string":"Almaden Research Center, IBM, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"[Almaden Res. Center, IBM, San Jose, CA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113793867","display_name":"Sriram Raghavan","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Raghavan","raw_affiliation_strings":["Almaden Research Center, IBM, San Jose, CA, USA","[Almaden Res. Center, IBM, San Jose, CA]"],"affiliations":[{"raw_affiliation_string":"Almaden Research Center, IBM, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"[Almaden Res. Center, IBM, San Jose, CA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102820528","display_name":"Rajasekar Krishnamurthy","orcid":"https://orcid.org/0000-0002-1245-4152"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajasekar Krishnamurthy","raw_affiliation_strings":["Almaden Research Center, IBM, San Jose, CA, USA","[Almaden Res. Center, IBM, San Jose, CA]"],"affiliations":[{"raw_affiliation_string":"Almaden Research Center, IBM, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"[Almaden Res. Center, IBM, San Jose, CA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076801334","display_name":"Huaiyu Zhu","orcid":"https://orcid.org/0000-0001-6918-4088"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Zhu","raw_affiliation_strings":["Almaden Research Center, IBM, San Jose, CA, USA","[Almaden Res. Center, IBM, San Jose, CA]"],"affiliations":[{"raw_affiliation_string":"Almaden Research Center, IBM, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"[Almaden Res. Center, IBM, San Jose, CA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010223683","display_name":"Shivakumar Vaithyanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivakumar Vaithyanathan","raw_affiliation_strings":["Almaden Research Center, IBM, San Jose, CA, USA","[Almaden Res. Center, IBM, San Jose, CA]"],"affiliations":[{"raw_affiliation_string":"Almaden Research Center, IBM, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"[Almaden Res. Center, IBM, San Jose, CA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074416632"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":43.7333,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.99771886,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"933","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9955000281333923,"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":0.7666528224945068},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6900738477706909},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.5451452732086182},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.5288335680961609},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49603399634361267},{"id":"https://openalex.org/keywords/algebraic-expression","display_name":"Algebraic expression","score":0.47474414110183716},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43890896439552307},{"id":"https://openalex.org/keywords/algebraic-number","display_name":"Algebraic number","score":0.42989420890808105},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.42520660161972046},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3914734423160553},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33461302518844604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26361218094825745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23918235301971436},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1665343940258026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14073330163955688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666528224945068},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6900738477706909},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.5451452732086182},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.5288335680961609},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49603399634361267},{"id":"https://openalex.org/C18912844","wikidata":"https://www.wikidata.org/wiki/Q4724001","display_name":"Algebraic expression","level":3,"score":0.47474414110183716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43890896439552307},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.42989420890808105},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.42520660161972046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3914734423160553},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33461302518844604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26361218094825745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23918235301971436},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1665343940258026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14073330163955688},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icde.2008.4497502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1026.259","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1026.259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Huaiyu_Zhu2/publication/4330935_An_Algebraic_Approach_to_Rule-Based_Information_Extraction/links/004635318c47308f2a000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.5676","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.5676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.almaden.ibm.com/software/projects/avatar/icde2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W158294556","https://openalex.org/W165944615","https://openalex.org/W1531918044","https://openalex.org/W1534730506","https://openalex.org/W1540589956","https://openalex.org/W1563062065","https://openalex.org/W1607983314","https://openalex.org/W1662519165","https://openalex.org/W1674493795","https://openalex.org/W1969595233","https://openalex.org/W1997703234","https://openalex.org/W2022760666","https://openalex.org/W2030408698","https://openalex.org/W2096797897","https://openalex.org/W2103224511","https://openalex.org/W2128375099","https://openalex.org/W2144358319","https://openalex.org/W2144416276","https://openalex.org/W2147880316","https://openalex.org/W2153329411","https://openalex.org/W2159491434","https://openalex.org/W2161484642","https://openalex.org/W4231867741","https://openalex.org/W6631918358","https://openalex.org/W6633761632","https://openalex.org/W6637233095","https://openalex.org/W6642518305","https://openalex.org/W6681288647","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W2563334590","https://openalex.org/W2807616588","https://openalex.org/W3094387502","https://openalex.org/W2922478741","https://openalex.org/W2119827098","https://openalex.org/W2052853109","https://openalex.org/W2101092231","https://openalex.org/W2367919820","https://openalex.org/W2952430269","https://openalex.org/W4297878330"],"abstract_inverted_index":{"Traditional":[0],"approaches":[1],"to":[2,22,41],"rule-based":[3,42,65],"information":[4],"extraction":[5,66],"(IE)":[6],"have":[7,19],"primarily":[8],"been":[9],"based":[10],"on":[11],"regular":[12],"expression":[13],"grammars.":[14],"However,":[15],"these":[16,46],"grammar-based":[17],"systems":[18],"difficulty":[20],"scaling":[21],"large":[23,27],"data":[24,70],"sets":[25],"and":[26,79],"numbers":[28],"of":[29,54,76,89,98],"rules.":[30],"Inspired":[31],"by":[32,59,85,101],"traditional":[33],"database":[34],"research,":[35],"we":[36,93],"propose":[37,80],"an":[38],"algebraic":[39],"approach":[40,100],"IE":[43],"that":[44],"addresses":[45],"scalability":[47],"issues":[48],"through":[49],"query":[50],"optimization.":[51],"The":[52],"operators":[53,75],"our":[55,60,77,90,99],"algebra":[56,78],"are":[57],"motivated":[58,84],"experience":[61],"in":[62],"building":[63],"several":[64,81],"programs":[67],"over":[68,104],"diverse":[69],"sets.":[71],"We":[72],"present":[73],"the":[74,86,95],"optimization":[82],"strategies":[83],"text-specific":[87],"characteristics":[88],"operators.":[91],"Finally":[92],"validate":[94],"potential":[96],"benefits":[97],"extensive":[102],"experiments":[103],"real-world":[105],"blog":[106],"data.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}