{"id":"https://openalex.org/W2976672264","doi":"https://doi.org/10.1145/3341981.3344236","title":"Simulating CLIR Translation Resource Scarcity using High-resource Languages","display_name":"Simulating CLIR Translation Resource Scarcity using High-resource Languages","publication_year":2019,"publication_date":"2019-09-26","ids":{"openalex":"https://openalex.org/W2976672264","doi":"https://doi.org/10.1145/3341981.3344236","mag":"2976672264"},"language":"en","primary_location":{"id":"doi:10.1145/3341981.3344236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344236","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344236","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344236","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010532614","display_name":"Hamed Bonab","orcid":"https://orcid.org/0000-0003-2811-706X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hamed Bonab","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037538509","display_name":"Ramesh K. Sitaraman","orcid":"https://orcid.org/0000-0003-0558-6875"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramesh Sitaraman","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010532614"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.4335,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72373654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9973999857902527,"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":0.8092492818832397},{"id":"https://openalex.org/keywords/swahili","display_name":"Swahili","score":0.7960131168365479},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.5722442865371704},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5500463843345642},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5496047139167786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49999189376831055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4621805250644684},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43315961956977844},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22216179966926575},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19027987122535706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092492818832397},{"id":"https://openalex.org/C2779913364","wikidata":"https://www.wikidata.org/wiki/Q7838","display_name":"Swahili","level":2,"score":0.7960131168365479},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.5722442865371704},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5500463843345642},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5496047139167786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49999189376831055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4621805250644684},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43315961956977844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22216179966926575},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19027987122535706},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341981.3344236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344236","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344236","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3341981.3344236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344236","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344236","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1503666391","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G656068760","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G6928934976","display_name":null,"funder_award_id":"14775","funder_id":"https://openalex.org/F4320307943","funder_display_name":"Raytheon Company"}],"funders":[{"id":"https://openalex.org/F4320307943","display_name":"Raytheon Company","ror":"https://ror.org/0354t7b78"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2976672264.pdf","grobid_xml":"https://content.openalex.org/works/W2976672264.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W70716795","https://openalex.org/W574924521","https://openalex.org/W1481701457","https://openalex.org/W1482214997","https://openalex.org/W2006672970","https://openalex.org/W2021314087","https://openalex.org/W2056989505","https://openalex.org/W2066651136","https://openalex.org/W2068297964","https://openalex.org/W2118724639","https://openalex.org/W2142756035","https://openalex.org/W2154200620","https://openalex.org/W2156985047","https://openalex.org/W2168801328","https://openalex.org/W2252046065","https://openalex.org/W2299662909","https://openalex.org/W2611804663","https://openalex.org/W2629131222","https://openalex.org/W2672337983","https://openalex.org/W2741986357","https://openalex.org/W2800252929","https://openalex.org/W2803620078","https://openalex.org/W2952455395","https://openalex.org/W2953320089","https://openalex.org/W2963617771","https://openalex.org/W2975751652","https://openalex.org/W3021729051","https://openalex.org/W3104723404","https://openalex.org/W4210360333","https://openalex.org/W4241714703","https://openalex.org/W4245267204","https://openalex.org/W4255169101"],"related_works":["https://openalex.org/W2024870452","https://openalex.org/W4232455167","https://openalex.org/W2589694904","https://openalex.org/W2023610355","https://openalex.org/W1964726137","https://openalex.org/W2197846837","https://openalex.org/W2966567079","https://openalex.org/W3182526644","https://openalex.org/W2528678572","https://openalex.org/W2325982659"],"abstract_inverted_index":{"We":[0,54,97,108,143,183],"study":[1],"the":[2,9,35,48,71,99,102,110,127,180,197],"impact":[3,51],"of":[4,11,73,94,115,202],"translation":[5,41],"resource":[6],"scarcity":[7],"on":[8,39,196],"performance":[10],"cross-language":[12],"information":[13],"retrieval":[14],"(CLIR)":[15],"systems.":[16],"To":[17,132],"do":[18],"that,":[19],"we":[20,37,69,135],"develop":[21,65],"a":[22,76,83,113],"contrastive":[23],"analysis":[24],"framework":[25],"that":[26,50,56,66,126,174],"uses":[27],"high-resource":[28,60,84,154],"languages":[29,155,166],"to":[30,45,64,86,162],"simulate":[31,163,184],"low-resource":[32,78,90,165],"languages.":[33],"In":[34],"framework,":[36],"focus":[38],"parallel":[40],"corpora":[42,61],"and":[43,59,80,124,145,159,168,188,194],"aim":[44],"better":[46],"understand":[47],"factors":[49],"CLIR":[52,203],"performance.":[53],"argue":[55],"both":[57],"low-":[58],"are":[62,177],"needed":[63],"understanding.":[67],"Hence,":[68],"take":[70],"approach":[72,148],"starting":[74],"with":[75,112,120,140,149,186,190],"true":[77],"language":[79,85,175],"systematically":[81],"down-sampling":[82],"become":[87],"an":[88],"artificial":[89],"language-the":[91],"reverse":[92],"perspective":[93],"existing":[95],"research.":[96],"formalize":[98],"problem":[100,111,128],"as":[101],"Resource":[103],"Scarcity":[104],"Simulation":[105],"(RSS)":[106],"problem.":[107,182],"model":[109],"family":[114],"set":[116],"covering":[117],"problems,":[118],"formulate":[119],"integer":[121],"linear":[122],"programming,":[123],"prove":[125],"is":[129],"actually":[130],"NP-hard.":[131],"this":[133],"end,":[134],"provide":[136],"two":[137,164],"greedy":[138],"algorithms":[139],"polynomial":[141],"complexities.":[142],"compare":[144],"analyze":[146],"our":[147],"alternate":[150],"techniques":[151],"using":[152],"four":[153],"(French,":[156],"Italian,":[157],"German,":[158,187],"Finnish)":[160],"down-sampled":[161],"(Somali":[167],"Swahili).":[169],"Our":[170],"experimental":[171],"results":[172],"suggest":[173],"families":[176],"important":[178],"for":[179],"RSS":[181],"Somali":[185],"Swahili":[189],"Finnish,":[191],"achieving":[192],"98%":[193],"97%":[195],"similarity":[198],"percentage":[199],"in":[200],"terms":[201],"performance,":[204],"respectively.":[205]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}