{"id":"https://openalex.org/W2600077227","doi":"https://doi.org/10.1145/3038295","title":"Corpus-Based Translation Induction in Indian Languages Using Auxiliary Language Corpora from Wikipedia","display_name":"Corpus-Based Translation Induction in Indian Languages Using Auxiliary Language Corpora from Wikipedia","publication_year":2017,"publication_date":"2017-03-17","ids":{"openalex":"https://openalex.org/W2600077227","doi":"https://doi.org/10.1145/3038295","mag":"2600077227"},"language":"en","primary_location":{"id":"doi:10.1145/3038295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038295","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource 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/A5055723101","display_name":"Goutham Tholpadi","orcid":"https://orcid.org/0000-0002-2599-6161"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Goutham Tholpadi","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032650028","display_name":"Chiranjib Bhattacharyya","orcid":"https://orcid.org/0000-0003-2879-4933"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chiranjib Bhattacharyya","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026126465","display_name":"Shirish Shevade","orcid":"https://orcid.org/0009-0009-7202-6860"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shirish Shevade","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055723101"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.8306,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79780454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8614081144332886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.73846834897995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.690460205078125},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.6259245872497559},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.5715055465698242},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5188566446304321},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5171929597854614},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5148043036460876},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.49879956245422363},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49877142906188965},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4447941482067108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614081144332886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.73846834897995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.690460205078125},{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.6259245872497559},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.5715055465698242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5188566446304321},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5171929597854614},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5148043036460876},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.49879956245422363},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49877142906188965},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4447941482067108},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3038295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038295","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"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 and Low-Resource Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.iisc.ac.in:56899","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W23015468","https://openalex.org/W38126138","https://openalex.org/W108460122","https://openalex.org/W113606665","https://openalex.org/W119481552","https://openalex.org/W165057458","https://openalex.org/W236925592","https://openalex.org/W1482316958","https://openalex.org/W1541966623","https://openalex.org/W1567365482","https://openalex.org/W1590839732","https://openalex.org/W1626233182","https://openalex.org/W1693107767","https://openalex.org/W1762503104","https://openalex.org/W1833099394","https://openalex.org/W1964209958","https://openalex.org/W1972871876","https://openalex.org/W2003948532","https://openalex.org/W2006969979","https://openalex.org/W2024732135","https://openalex.org/W2033593667","https://openalex.org/W2037789405","https://openalex.org/W2042891399","https://openalex.org/W2058236194","https://openalex.org/W2067438047","https://openalex.org/W2072976288","https://openalex.org/W2077562320","https://openalex.org/W2080100102","https://openalex.org/W2081214258","https://openalex.org/W2086511124","https://openalex.org/W2091889711","https://openalex.org/W2099534719","https://openalex.org/W2102028293","https://openalex.org/W2102749417","https://openalex.org/W2103318667","https://openalex.org/W2104042555","https://openalex.org/W2105813426","https://openalex.org/W2111666304","https://openalex.org/W2117831564","https://openalex.org/W2118606687","https://openalex.org/W2119727789","https://openalex.org/W2120779048","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2124639706","https://openalex.org/W2133837072","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2141766660","https://openalex.org/W2143927888","https://openalex.org/W2148086098","https://openalex.org/W2149393279","https://openalex.org/W2153222072","https://openalex.org/W2154558620","https://openalex.org/W2155983311","https://openalex.org/W2157076169","https://openalex.org/W2158207953","https://openalex.org/W2158246688","https://openalex.org/W2167265720","https://openalex.org/W2170204377","https://openalex.org/W2250229103","https://openalex.org/W2250360382","https://openalex.org/W2250413370","https://openalex.org/W2251159649","https://openalex.org/W2251352461","https://openalex.org/W2252213301","https://openalex.org/W2252224218","https://openalex.org/W2293721133","https://openalex.org/W2321588627","https://openalex.org/W2998215494","https://openalex.org/W4210764005","https://openalex.org/W4256361765"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W2604275745","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W2985215540","https://openalex.org/W4307459710","https://openalex.org/W3155572818","https://openalex.org/W4293584592","https://openalex.org/W4285266806"],"abstract_inverted_index":{"Identifying":[0],"translations":[1,82],"from":[2,77,118],"comparable":[3,60,74,133],"corpora":[4,75,134],"is":[5],"a":[6,38,47,108,112,124,146,214],"well-known":[7],"problem":[8,31,58,197],"with":[9],"several":[10],"applications.":[11],"Existing":[12],"methods":[13],"rely":[14],"on":[15,131,175,186,211],"linguistic":[16],"tools":[17],"or":[18],"high-quality":[19,169],"corpora.":[20],"Absence":[21],"of":[22,42,59,107,114,198,220],"such":[23],"resources,":[24],"especially":[25],"in":[26,83,94,96,138,160,184,217],"Indian":[27],"languages,":[28],"makes":[29],"this":[30,53,161],"hard;":[32],"for":[33,44,50,127,148,172],"example,":[34],"state-of-the-art":[35],"techniques":[36],"achieve":[37],"mean":[39],"reciprocal":[40],"rank":[41],"0.66":[43],"English-Italian,":[45],"and":[46,86,122,203],"mere":[48],"0.187":[49],"Telugu-Kannada.":[51],"In":[52],"work,":[54],"we":[55,103,163],"address":[56],"the":[57,67,84,105,176,187,192,195,205,218],"corpora-based":[61],"translation":[62],"correspondence":[63],"induction":[64],"(CC-TCI)":[65],"when":[66],"only":[68],"resources":[69],"available":[70,166],"are":[71],"small":[72],"noisy":[73],"extracted":[76],"Wikipedia.":[78],"We":[79,140,190],"observe":[80],"that":[81],"source":[85],"target":[87],"languages":[88],"have":[89],"many":[90],"topically":[91,115],"related":[92,116],"words":[93,117],"common":[95],"other":[97],"\u201cauxiliary\u201d":[98],"languages.":[99],"To":[100,156],"model":[101],"this,":[102],"define":[104],"notion":[106],"translingual":[109],"theme":[110],",":[111],"set":[113],"auxiliary":[119],"language":[120],"corpora,":[121],"present":[123],"probabilistic":[125],"framework":[126],"CC-TCI.":[128],"Extensive":[129],"experiments":[130],"35":[132],"showed":[135],"dramatic":[136],"improvements":[137],"performance.":[139],"extend":[141],"these":[142],"ideas":[143],"to":[144,194],"propose":[145],"method":[147,193],"measuring":[149],"cross-lingual":[150,199],"semantic":[151],"relatedness":[152],"(CLSR)":[153],"between":[154],"words.":[155],"stimulate":[157],"further":[158],"research":[159],"area,":[162],"make":[164],"publicly":[165],"two":[167],"new":[168],"human-annotated":[170],"datasets":[171,178],"CLSR.":[173],"Experiments":[174],"CLSR":[177,188],"show":[179],"more":[180],"than":[181],"200%":[182],"improvement":[183,216],"correlation":[185],"task.":[189],"apply":[191],"real-world":[196],"Wikipedia":[200],"title":[201],"suggestion":[202],"build":[204],"WikiTSu":[206,212],"system.":[207],"A":[208],"user":[209],"study":[210],"shows":[213],"20%":[215],"quality":[219],"titles":[221],"suggested.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}