{"id":"https://openalex.org/W2098165490","doi":"https://doi.org/10.1145/1390749.1390756","title":"Rule based synonyms for entity extraction from noisy text","display_name":"Rule based synonyms for entity extraction from noisy text","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2098165490","doi":"https://doi.org/10.1145/1390749.1390756","mag":"2098165490"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5036606820","display_name":"Rema Ananthanarayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","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":["IN","US"],"is_corresponding":true,"raw_author_name":"Rema Ananthanarayanan","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058823844","display_name":"Vijil Chenthamarakshan","orcid":"https://orcid.org/0000-0001-7830-5777"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vijil Chenthamarakshan","raw_affiliation_strings":["IBM India Research Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065031367","display_name":"Prasad Deshpande","orcid":"https://orcid.org/0000-0001-6389-533X"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasad M Deshpande","raw_affiliation_strings":["IBM India Research Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110544974","display_name":"Raghuram Krishnapuram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghuram Krishnapuram","raw_affiliation_strings":["IBM India Research Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036606820"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":5.1484,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95139567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.861572802066803},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.8000869750976562},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.685928463935852},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6486454606056213},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6352083086967468},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5930666923522949},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5729171633720398},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5610292553901672},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5350841879844666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5324909090995789},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4803010821342468},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4699321687221527},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.11313149333000183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861572802066803},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.8000869750976562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.685928463935852},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6486454606056213},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6352083086967468},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5930666923522949},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5729171633720398},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5610292553901672},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5350841879844666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324909090995789},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4803010821342468},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4699321687221527},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.11313149333000183},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"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":23,"referenced_works":["https://openalex.org/W67066386","https://openalex.org/W86887328","https://openalex.org/W130948412","https://openalex.org/W278081246","https://openalex.org/W1482174963","https://openalex.org/W1547083634","https://openalex.org/W1548663377","https://openalex.org/W1554237613","https://openalex.org/W1567365482","https://openalex.org/W1574901103","https://openalex.org/W1659833910","https://openalex.org/W2029433174","https://openalex.org/W2055405704","https://openalex.org/W2066066594","https://openalex.org/W2082889357","https://openalex.org/W2100935296","https://openalex.org/W2113227740","https://openalex.org/W2128759588","https://openalex.org/W2147152072","https://openalex.org/W2166776180","https://openalex.org/W2243237654","https://openalex.org/W2598684926","https://openalex.org/W2953332543"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W3133906981","https://openalex.org/W3005865135","https://openalex.org/W3006227201","https://openalex.org/W3160627956","https://openalex.org/W2891522332","https://openalex.org/W2595836257"],"abstract_inverted_index":{"Identification":[0],"of":[1,42,49,63,68,83,104,153,213,217],"named":[2,157,207,219],"entities":[3,208,220],"such":[4,72],"as":[5,65,92,120],"person,":[6],"organization":[7],"and":[8,53,96,167,183,209],"product":[9],"names":[10],"from":[11],"text":[12,64],"is":[13,75],"an":[14,69],"important":[15],"task":[16,139],"in":[17,30,71,156,164,191],"information":[18],"extraction.":[19],"In":[20,110,195],"many":[21],"domains,":[22],"the":[23,89,102,105,128,137,142,161,180,188,192,199,211],"same":[24],"entity":[25,70,94,158,165],"could":[26],"be":[27,123],"referred":[28],"to":[29,34,107,126,131,187],"multiple":[31],"ways":[32],"due":[33],"variations":[35,41,163],"introduced":[36],"by":[37,221],"different":[38,226],"user":[39],"groups,":[40],"spellings":[43],"across":[44],"regions":[45],"or":[46],"cultures,":[47],"usage":[48],"abbreviations,":[50],"typographical":[51],"errors":[52],"other":[54],"reasons":[55],"associated":[56],"with":[57],"conventional":[58],"usage.":[59],"Identifying":[60],"a":[61,66,81,132,151],"piece":[62],"mention":[67],"noisy":[73],"data":[74,193],"difficult,":[76],"even":[77],"if":[78],"we":[79,113,176,197,203],"have":[80],"dictionary":[82],"possible":[84,162],"entities.":[85],"Previous":[86],"approaches":[87],"treat":[88],"synonym":[90,129],"problem":[91,130],"part":[93],"disambiguation":[95,138],"use":[97,101],"learning-based":[98],"methods":[99],"that":[100,115,202],"context":[103],"words":[106],"identify":[108],"synonyms.":[109],"this":[111],"paper,":[112],"show":[114],"existing":[116],"domain":[117],"knowledge,":[118],"encoded":[119],"rules,":[121,175],"can":[122],"used":[124],"effectively":[125],"address":[127],"considerable":[133],"extent.":[134],"This":[135],"makes":[136],"simpler,":[140],"without":[141],"need":[143],"for":[144,170,179,205,224],"much":[145],"training":[146],"data.":[147],"We":[148],"look":[149],"at":[150],"subset":[152],"application":[154],"scenarios":[155],"extraction,":[159],"categorize":[160],"names,":[166],"define":[168],"rules":[169],"each":[171],"category.":[172],"Using":[173],"these":[174,185],"generate":[177],"synonyms":[178,186,223],"canonical":[181],"list":[182],"match":[184],"actual":[189],"occurrence":[190],"sets.":[194],"particular,":[196],"describe":[198],"rule":[200],"categories":[201],"developed":[204],"several":[206],"report":[210],"results":[212],"applying":[214],"our":[215],"technique":[216],"extracting":[218],"generating":[222],"two":[225],"domains.":[227]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}