{"id":"https://openalex.org/W2963587420","doi":"https://doi.org/10.1145/3329713","title":"Matching Graph, a Method for Extracting Parallel Information from Comparable Corpora","display_name":"Matching Graph, a Method for Extracting Parallel Information from Comparable Corpora","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963587420","doi":"https://doi.org/10.1145/3329713","mag":"2963587420"},"language":"en","primary_location":{"id":"doi:10.1145/3329713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3329713","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/A5044315362","display_name":"Somayeh Bakhshaei","orcid":null},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Somayeh Bakhshaei","raw_affiliation_strings":["Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043747222","display_name":"Reza Safabakhsh","orcid":"https://orcid.org/0000-0002-4937-8026"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Reza Safabakhsh","raw_affiliation_strings":["Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047428600","display_name":"Shahram Khadivi","orcid":"https://orcid.org/0000-0001-5499-6542"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Shahram Khadivi","raw_affiliation_strings":["Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044315362"],"corresponding_institution_ids":["https://openalex.org/I158248296"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07626189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"1","first_page":"1","last_page":"29"},"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":0.9997000098228455,"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":0.9943000078201294,"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":0.8509688377380371},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7736490368843079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6776025295257568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6558687090873718},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.5831748247146606},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5550920963287354},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5058281421661377},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5044454336166382},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4629806578159332},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.43454283475875854},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4204975664615631},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.414778470993042},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21511799097061157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09509497880935669},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09148713946342468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509688377380371},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7736490368843079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6776025295257568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6558687090873718},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.5831748247146606},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5550920963287354},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5058281421661377},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5044454336166382},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4629806578159332},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.43454283475875854},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4204975664615631},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.414778470993042},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21511799097061157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09509497880935669},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09148713946342468},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3329713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3329713","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":117,"referenced_works":["https://openalex.org/W13412558","https://openalex.org/W38126138","https://openalex.org/W75158669","https://openalex.org/W77273554","https://openalex.org/W92412080","https://openalex.org/W113606665","https://openalex.org/W149643677","https://openalex.org/W178169250","https://openalex.org/W342285082","https://openalex.org/W574870997","https://openalex.org/W1490960179","https://openalex.org/W1492234127","https://openalex.org/W1498990157","https://openalex.org/W1508577659","https://openalex.org/W1523140216","https://openalex.org/W1524281572","https://openalex.org/W1541966623","https://openalex.org/W1570490112","https://openalex.org/W1596108646","https://openalex.org/W1607035479","https://openalex.org/W1693107767","https://openalex.org/W1828724394","https://openalex.org/W1889220380","https://openalex.org/W1988012253","https://openalex.org/W2006969979","https://openalex.org/W2033593667","https://openalex.org/W2038721957","https://openalex.org/W2041232209","https://openalex.org/W2041701373","https://openalex.org/W2072976288","https://openalex.org/W2074244346","https://openalex.org/W2080972498","https://openalex.org/W2084277454","https://openalex.org/W2091889711","https://openalex.org/W2096424679","https://openalex.org/W2099534719","https://openalex.org/W2100235303","https://openalex.org/W2101105183","https://openalex.org/W2102749417","https://openalex.org/W2107695330","https://openalex.org/W2111666304","https://openalex.org/W2115008667","https://openalex.org/W2115367993","https://openalex.org/W2117198860","https://openalex.org/W2117831564","https://openalex.org/W2118606687","https://openalex.org/W2121415745","https://openalex.org/W2124807415","https://openalex.org/W2125803669","https://openalex.org/W2126725946","https://openalex.org/W2137170544","https://openalex.org/W2137996024","https://openalex.org/W2138437702","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2140903445","https://openalex.org/W2146574666","https://openalex.org/W2148086098","https://openalex.org/W2155603234","https://openalex.org/W2155983311","https://openalex.org/W2156208571","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2159441553","https://openalex.org/W2161192091","https://openalex.org/W2163922914","https://openalex.org/W2165903086","https://openalex.org/W2172268343","https://openalex.org/W2211796614","https://openalex.org/W2250209789","https://openalex.org/W2250229103","https://openalex.org/W2250413370","https://openalex.org/W2250442833","https://openalex.org/W2250863245","https://openalex.org/W2250977808","https://openalex.org/W2251249103","https://openalex.org/W2251302843","https://openalex.org/W2251449587","https://openalex.org/W2251569308","https://openalex.org/W2251742274","https://openalex.org/W2252039676","https://openalex.org/W2275683873","https://openalex.org/W2339623852","https://openalex.org/W2403566681","https://openalex.org/W2404244834","https://openalex.org/W2421014960","https://openalex.org/W2422372688","https://openalex.org/W2430909973","https://openalex.org/W2435130738","https://openalex.org/W2483327705","https://openalex.org/W2554554704","https://openalex.org/W2600077227","https://openalex.org/W2601748485","https://openalex.org/W2607403128","https://openalex.org/W2615499310","https://openalex.org/W2770789184","https://openalex.org/W2884815824","https://openalex.org/W2891589612","https://openalex.org/W2912218307","https://openalex.org/W2913602408","https://openalex.org/W2918138400","https://openalex.org/W2930957955","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2952230511","https://openalex.org/W2962684168","https://openalex.org/W2968573267","https://openalex.org/W2998215494","https://openalex.org/W3105899356","https://openalex.org/W3122255303","https://openalex.org/W3197645311","https://openalex.org/W4205509257","https://openalex.org/W4206070039","https://openalex.org/W4237040408","https://openalex.org/W4253352728","https://openalex.org/W6660124337","https://openalex.org/W6683738474"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W2395641992","https://openalex.org/W2807475932","https://openalex.org/W3021126373","https://openalex.org/W4280571180","https://openalex.org/W2903057408","https://openalex.org/W92588874","https://openalex.org/W2963991316","https://openalex.org/W2786253471","https://openalex.org/W3175595715"],"abstract_inverted_index":{"Comparable":[0],"corpora":[1],"are":[2,16,137],"valuable":[3],"alternatives":[4],"for":[5,19,33,77,121,171,184,189],"the":[6,48,55,61,82,89,102,110,130,134,144,165],"expensive":[7],"parallel":[8,13,37,112,119,157],"corpora.":[9],"They":[10],"comprise":[11],"informative":[12],"fragments":[14,38,113,132,167],"that":[15,88,129,152,163],"useful":[17],"resources":[18],"different":[20],"natural":[21],"language":[22,78,108],"processing":[23],"tasks.":[24],"In":[25],"this":[26],"work,":[27],"a":[28,40,52,68,74,147,156],"generative":[29],"model":[30,50,76],"is":[31,51,153,161],"proposed":[32,49],"efficient":[34],"extraction":[35],"of":[36,42,47,60,118,143,146,181],"from":[39,81],"pair":[41],"comparable":[43],"documents.":[44],"The":[45,58],"core":[46],"graph":[53],"called":[54],"Matching":[56,62,90],"Graph.":[57],"ability":[59],"Graph":[63,91],"to":[64,101,139,178],"be":[65,115],"trained":[66,154],"on":[67,104,155,192],"small":[69],"initial":[70],"seed":[71],"makes":[72],"it":[73,160],"proper":[75],"pairs":[79],"suffering":[80],"scarce":[83],"resource":[84],"problem.":[85],"Experiments":[86],"show":[87],"performs":[92],"significantly":[93],"better":[94],"than":[95],"other":[96],"recently":[97],"published":[98],"models.":[99],"According":[100],"experiments":[103],"English-Persian":[105,185],"and":[106,186],"Arabic-Persian":[107,190],"pairs,":[109],"extracted":[111,131,166],"can":[114],"used":[116],"instead":[117],"data":[120],"training":[122,172],"statistical":[123,148,173],"machine":[124,149,174],"translation":[125,150,175,191],"systems.":[126],"Results":[127],"reveal":[128],"in":[133],"best":[135],"case":[136],"able":[138],"retrieve":[140],"about":[141,182,187],"90%":[142],"information":[145,170],"system":[151],"corpus.":[158],"Moreover,":[159],"shown":[162],"using":[164],"as":[168],"additional":[169],"systems":[176],"leads":[177],"an":[179],"improvement":[180],"2%":[183],"1%":[188],"BLEU":[193],"score.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}