{"id":"https://openalex.org/W2159491434","doi":"https://doi.org/10.1109/icde.2006.55","title":"Efficient Batch Top-k Search for Dictionary-based Entity Recognition","display_name":"Efficient Batch Top-k Search for Dictionary-based Entity Recognition","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2159491434","doi":"https://doi.org/10.1109/icde.2006.55","mag":"2159491434"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2006.55","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2006.55","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Conference on Data Engineering (ICDE'06)","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/A5077370881","display_name":"Amit Singh Chandel","orcid":"https://orcid.org/0000-0001-5732-4725"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A. Chandel","raw_affiliation_strings":["IIT, Bombay, India","IIT, Bombay#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT, Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT, Bombay#TAB#","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063227098","display_name":"Pradeep Nagesh","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P.C. Nagesh","raw_affiliation_strings":["IIT, Bombay, India","IIT, Bombay#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT, Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT, Bombay#TAB#","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Sarawagi","raw_affiliation_strings":["IIT, Bombay, India","IIT, Bombay#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT, Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT, Bombay#TAB#","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":10.84,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.98496505,"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":"28","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.996399998664856,"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":0.826534628868103},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.6623280048370361},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6467679142951965},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6453646421432495},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5836416482925415},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5546862483024597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4341222643852234},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38145941495895386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33919888734817505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3306560814380646},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.16714218258857727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826534628868103},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.6623280048370361},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6467679142951965},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6453646421432495},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5836416482925415},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5546862483024597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341222643852234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38145941495895386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33919888734817505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3306560814380646},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.16714218258857727},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2006.55","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2006.55","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"22nd International Conference on Data Engineering (ICDE'06)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.774","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.it.iitb.ac.in/~sunita/papers/icde06b.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":28,"referenced_works":["https://openalex.org/W1527283363","https://openalex.org/W1534730506","https://openalex.org/W1535279741","https://openalex.org/W1542218590","https://openalex.org/W1568339100","https://openalex.org/W1575332430","https://openalex.org/W1953828586","https://openalex.org/W1969483458","https://openalex.org/W2048468185","https://openalex.org/W2100796029","https://openalex.org/W2105423800","https://openalex.org/W2124410446","https://openalex.org/W2127675794","https://openalex.org/W2143349571","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2158188757","https://openalex.org/W2160484851","https://openalex.org/W2395895772","https://openalex.org/W2666600683","https://openalex.org/W3004248957","https://openalex.org/W6631549090","https://openalex.org/W6631918358","https://openalex.org/W6634115791","https://openalex.org/W6634336062","https://openalex.org/W6681291824","https://openalex.org/W6682082992","https://openalex.org/W6683226453"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2021800959"],"abstract_inverted_index":{"We":[0,44,86],"consider":[1],"the":[2,25,28,37,41,50,93,113],"problem":[3,48],"of":[4,15,27,32,36,52,64,75,92,120],"speeding":[5],"up":[6],"Entity":[7],"Recognition":[8],"systems":[9,23],"that":[10],"exploit":[11],"existing":[12],"large":[13],"databases":[14],"structured":[16],"entities":[17,99],"to":[18,102,123],"improve":[19],"extraction":[20],"accuracy.":[21],"These":[22],"require":[24],"computation":[26],"maximum":[29],"similarity":[30],"scores":[31],"several":[33],"overlapping":[34,56],"segments":[35],"input":[38],"text":[39],"with":[40,49,104],"entity":[42],"database.":[43],"formulate":[45],"a":[46,62,73,89,118],"Batch-Top-K":[47],"goal":[51],"sharing":[53],"computations":[54],"across":[55],"segments.":[57],"Our":[58],"proposed":[59],"algorithm":[60,96],"performs":[61],"factor":[63,74,119],"three":[65],"faster":[66],"than":[67,78],"independent":[68],"Top-K":[69],"queries":[70],"and":[71],"only":[72],"two":[76],"slower":[77],"an":[79],"unachievable":[80],"lower":[81],"bound":[82],"on":[83,108],"total":[84,114],"cost.":[85],"then":[87],"propose":[88],"novel":[90],"modification":[91],"popular":[94],"Viterbi":[95],"for":[97],"recognizing":[98],"so":[100],"as":[101],"work":[103],"easily":[105],"computable":[106],"bounds":[107],"match":[109],"scores,":[110],"thereby":[111],"reducing":[112],"inference":[115],"time":[116],"by":[117],"eight":[121],"compared":[122],"stateof-":[124],"the-art":[125],"methods.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}