{"id":"https://openalex.org/W2054460891","doi":"https://doi.org/10.1145/1838751.1838754","title":"An Information-Extraction System for Urdu---A Resource-Poor Language","display_name":"An Information-Extraction System for Urdu---A Resource-Poor Language","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2054460891","doi":"https://doi.org/10.1145/1838751.1838754","mag":"2054460891"},"language":"en","primary_location":{"id":"doi:10.1145/1838751.1838754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1838751.1838754","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-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/A5001750776","display_name":"Smruthi Mukund","orcid":"https://orcid.org/0009-0004-4550-6758"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Smruthi Mukund","raw_affiliation_strings":["State University of New York at Buffalo"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063869451","display_name":"Rohini K. Srihari","orcid":"https://orcid.org/0000-0001-7454-6872"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohini Srihari","raw_affiliation_strings":["State University of New York at Buffalo"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091723554","display_name":"Erik Peterson","orcid":"https://orcid.org/0000-0002-2033-007X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Peterson","raw_affiliation_strings":["Janya, Inc"],"affiliations":[{"raw_affiliation_string":"Janya, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001750776"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":2.787,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.91069353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"4","first_page":"1","last_page":"43"},"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9890999794006348,"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":0.8877930641174316},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.7751247882843018},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7019880414009094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6982000470161438},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6010123491287231},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5607051253318787},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5600167512893677},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5248770117759705},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.48150762915611267},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4625737965106964},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.44241607189178467},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.365982323884964},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.1666734218597412},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10643771290779114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.08095329999923706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8877930641174316},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.7751247882843018},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7019880414009094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6982000470161438},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6010123491287231},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5607051253318787},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5600167512893677},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5248770117759705},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.48150762915611267},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4625737965106964},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.44241607189178467},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.365982323884964},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.1666734218597412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10643771290779114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.08095329999923706},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1838751.1838754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1838751.1838754","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.7220","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.7220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cedar.buffalo.edu/~rohini/Papers/ACM-TALIP.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W667520","https://openalex.org/W14574270","https://openalex.org/W32715122","https://openalex.org/W89200743","https://openalex.org/W103729224","https://openalex.org/W118585533","https://openalex.org/W142344189","https://openalex.org/W152203974","https://openalex.org/W165579794","https://openalex.org/W186939825","https://openalex.org/W402681447","https://openalex.org/W592196944","https://openalex.org/W900993354","https://openalex.org/W1487630328","https://openalex.org/W1496485126","https://openalex.org/W1505083828","https://openalex.org/W1520377376","https://openalex.org/W1524281572","https://openalex.org/W1531859941","https://openalex.org/W1542706181","https://openalex.org/W1572758415","https://openalex.org/W1587977534","https://openalex.org/W1593502373","https://openalex.org/W1606503788","https://openalex.org/W1606813020","https://openalex.org/W1628767011","https://openalex.org/W1629870923","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1892324236","https://openalex.org/W1968151119","https://openalex.org/W1992696103","https://openalex.org/W2004110071","https://openalex.org/W2009266707","https://openalex.org/W2013623275","https://openalex.org/W2020448136","https://openalex.org/W2028581349","https://openalex.org/W2056159894","https://openalex.org/W2056724340","https://openalex.org/W2062476972","https://openalex.org/W2081687495","https://openalex.org/W2090362702","https://openalex.org/W2096204319","https://openalex.org/W2099253769","https://openalex.org/W2100935296","https://openalex.org/W2103015765","https://openalex.org/W2103443012","https://openalex.org/W2106750491","https://openalex.org/W2107913424","https://openalex.org/W2115639608","https://openalex.org/W2123512824","https://openalex.org/W2127589427","https://openalex.org/W2128228208","https://openalex.org/W2132880762","https://openalex.org/W2132903501","https://openalex.org/W2135843243","https://openalex.org/W2136176329","https://openalex.org/W2139809176","https://openalex.org/W2140016149","https://openalex.org/W2141099517","https://openalex.org/W2143345705","https://openalex.org/W2144839729","https://openalex.org/W2147116133","https://openalex.org/W2147880316","https://openalex.org/W2163377725","https://openalex.org/W2165920695","https://openalex.org/W2174011386","https://openalex.org/W2187579899","https://openalex.org/W2404741839","https://openalex.org/W2414140881","https://openalex.org/W2416749667","https://openalex.org/W2536236635","https://openalex.org/W2600299847","https://openalex.org/W2615497679","https://openalex.org/W2741609678","https://openalex.org/W2804859675","https://openalex.org/W2899606919","https://openalex.org/W2951562155","https://openalex.org/W2951956562","https://openalex.org/W2953332543","https://openalex.org/W3006543648","https://openalex.org/W3145501851","https://openalex.org/W4250788613","https://openalex.org/W4285719527","https://openalex.org/W6636270844","https://openalex.org/W6683955732","https://openalex.org/W6686553991","https://openalex.org/W6774174130","https://openalex.org/W7052656108"],"related_works":["https://openalex.org/W190438618","https://openalex.org/W2990791508","https://openalex.org/W4285154531","https://openalex.org/W2032007337","https://openalex.org/W4288286832","https://openalex.org/W2954982483","https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W135458787","https://openalex.org/W1884363728"],"abstract_inverted_index":{"There":[0],"has":[1,28,245],"been":[2,88,246],"an":[3,151],"increase":[4],"in":[5,26,91,105,112],"the":[6,12,16,33,99,198,207,232,239,258,265,268],"amount":[7],"of":[8,18,110,136,145,161,238,267],"multilingual":[9],"text":[10,242],"on":[11,32,165],"Internet":[13],"due":[14],"to":[15,75,124,127,149,183,196,230],"proliferation":[17],"news":[19,125],"sources":[20,118,182],"and":[21,48,50,70,73,81,122,132,159,189,219],"blogs.":[22],"The":[23,108,143,192,253],"Urdu":[24,102,113,155,235,241],"language,":[25,226],"particular,":[27],"experienced":[29],"explosive":[30],"growth":[31],"Web.":[34],"Text":[35],"mining":[36],"for":[37,97,101,154,212],"information":[38,169],"discovery,":[39],"which":[40,166],"includes":[41,115],"tasks":[42,109],"such":[43,64,77,93,119,215],"as":[44,65,78,120,216],"identifying":[45],"topics,":[46],"relationships":[47],"events,":[49],"sentiment":[51],"analysis,":[52],"requires":[53,138],"sophisticated":[54],"natural":[55],"language":[56],"processing":[57,243],"(NLP).":[58],"NLP":[59,95,114,141,152],"systems":[60,96],"begin":[61],"with":[62],"modules":[63,76,244],"word":[66],"segmentation,":[67],"part-of-speech":[68],"tagging,":[69],"morphological":[71],"analysis":[72,164],"progress":[74],"shallow":[79],"parsing":[80],"named":[82,186],"entity":[83,187],"tagging.":[84],"While":[85],"there":[86],"have":[87,260],"considerable":[89],"advances":[90],"developing":[92],"comprehensive":[94],"English,":[98],"work":[100,147],"is":[103,148,157,203],"still":[104],"its":[106],"infancy.":[107],"interest":[111],"analyzing":[116],"data":[117,194],"blogs":[121],"comments":[123],"articles":[126],"provide":[128],"insight":[129],"into":[130,248],"social":[131],"human":[133],"behavior.":[134],"All":[135],"this":[137,146],"a":[139,223,249],"robust":[140],"system.":[142],"objective":[144],"develop":[150],"infrastructure":[153],"that":[156,257],"customizable":[158],"capable":[160],"providing":[162],"basic":[163],"more":[167],"advanced":[168],"extraction":[170],"tools":[171],"can":[172],"be":[173],"built.":[174],"This":[175],"system":[176],"assimilates":[177],"resources":[178,210],"from":[179,222],"various":[180],"online":[181],"facilitate":[184],"improved":[185],"tagging":[188],"Urdu-to-English":[190],"transliteration.":[191],"annotated":[193,234],"required":[195],"train":[197],"learning":[199,218],"models":[200],"used":[201],"here":[202],"acquired":[204],"by":[205],"standardizing":[206],"currently":[208],"limited":[209],"available":[211,233],"Urdu.":[213],"Techniques":[214],"bootstrap":[217],"resource":[220],"sharing":[221],"syntactically":[224],"similar":[225],"Hindi,":[227],"are":[228],"explored":[229],"augment":[231],"data.":[236],"Each":[237],"new":[240],"integrated":[247],"general":[250],"text-mining":[251],"platform.":[252],"evaluations":[254],"performed":[255],"demonstrate":[256],"accuracies":[259],"either":[261],"met":[262],"or":[263],"exceeded":[264],"state":[266],"art.":[269]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
