{"id":"https://openalex.org/W4408973331","doi":"https://doi.org/10.1007/s10579-025-09819-2","title":"Semantic processing for Urdu: corpus creation, parsing, and generation","display_name":"Semantic processing for Urdu: corpus creation, parsing, and generation","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408973331","doi":"https://doi.org/10.1007/s10579-025-09819-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-025-09819-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09819-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09819-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09819-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008746407","display_name":"Muhammad Saad Amin","orcid":"https://orcid.org/0000-0002-7002-9373"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Muhammad Saad Amin","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696673","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-8020-6142"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043355817","display_name":"Luca Anselma","orcid":"https://orcid.org/0000-0003-2292-6480"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Anselma","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013143796","display_name":"Alessandro Mazzei","orcid":"https://orcid.org/0000-0003-3072-0108"},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Mazzei","raw_affiliation_strings":["Department of Computer Science, University of Turin, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002288369","display_name":"Johan Bos","orcid":"https://orcid.org/0000-0002-9079-5438"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johan Bos","raw_affiliation_strings":["Center for Language and Cognition, University of Groningen, Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Cognition, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008746407"],"corresponding_institution_ids":["https://openalex.org/I55143463"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":3.6601,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92436003,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"59","issue":"3","first_page":"2469","last_page":"2500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T13629","display_name":"Text Readability and Simplification","score":0.9926999807357788,"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/urdu","display_name":"Urdu","score":0.8300654888153076},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7679814100265503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205710411071777},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7174611687660217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.603849470615387},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.376755028963089}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.8300654888153076},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7679814100265503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205710411071777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7174611687660217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.603849470615387},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.376755028963089},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10579-025-09819-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09819-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09819-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:publications/381bb9f2-76c9-4e02-9f66-20e973741e49","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/381bb9f2-76c9-4e02-9f66-20e973741e49","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Amin, M S, Zhang, X, Anselma, L, Mazzei, A & Bos, J 2025, 'Semantic processing for Urdu : Corpus creation, parsing, and generation', Language Resources and Evaluation, vol. 59, pp. 2469-2500. https://doi.org/10.1007/s10579-025-09819-2","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/381bb9f2-76c9-4e02-9f66-20e973741e49","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/381bb9f2-76c9-4e02-9f66-20e973741e49","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Amin, M S, Zhang, X, Anselma, L, Mazzei, A & Bos, J 2025, 'Semantic processing for Urdu : Corpus creation, parsing, and generation', Language Resources and Evaluation, vol. 59, pp. 2469-2500. https://doi.org/10.1007/s10579-025-09819-2","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10579-025-09819-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-025-09819-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-025-09819-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324041","display_name":"Universit\u00e0 degli Studi di Torino","ror":"https://ror.org/048tbm396"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408973331.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1555829539","https://openalex.org/W1579035156","https://openalex.org/W1968151119","https://openalex.org/W2007871210","https://openalex.org/W2033194278","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2131429178","https://openalex.org/W2250342921","https://openalex.org/W2250375035","https://openalex.org/W2250741443","https://openalex.org/W2251143283","https://openalex.org/W2252123671","https://openalex.org/W2252172629","https://openalex.org/W2468355276","https://openalex.org/W2511149676","https://openalex.org/W2788465415","https://openalex.org/W2798546337","https://openalex.org/W2949442273","https://openalex.org/W2954996726","https://openalex.org/W2971037578","https://openalex.org/W2981852735","https://openalex.org/W2996696903","https://openalex.org/W2999218890","https://openalex.org/W3034808961","https://openalex.org/W3034812953","https://openalex.org/W3034999214","https://openalex.org/W3087952348","https://openalex.org/W3103699753","https://openalex.org/W3117132370","https://openalex.org/W3164045210","https://openalex.org/W3169483174","https://openalex.org/W3173115050","https://openalex.org/W3174547290","https://openalex.org/W3174828871","https://openalex.org/W3183291103","https://openalex.org/W3212104012","https://openalex.org/W4214877181","https://openalex.org/W4285228888","https://openalex.org/W4306295214","https://openalex.org/W4311891308","https://openalex.org/W4313579429","https://openalex.org/W4322718191","https://openalex.org/W4385571874","https://openalex.org/W4385572488","https://openalex.org/W4395065284","https://openalex.org/W4411630034","https://openalex.org/W6634255785","https://openalex.org/W6674691768","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W7025021118","https://openalex.org/W7028010891","https://openalex.org/W7062055868"],"related_works":["https://openalex.org/W1588484110","https://openalex.org/W1566901819","https://openalex.org/W604003083","https://openalex.org/W597280011","https://openalex.org/W2250347524","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W1502858101","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Discourse":[1],"representation":[2],"structure":[3,105],"(DRS),":[4],"a":[5,86,160,193],"formal":[6,61,72],"meaning":[7,62,73,154],"representation,":[8],"has":[9],"been":[10],"used":[11],"for":[12,25,32,48,53,80,156,204,218,237],"both":[13,90],"semantic":[14,55,162,189,206,219],"parsing":[15,56,220],"and":[16,21,31,39,64,93,106,135,164,173,210,225,234],"natural":[17,65],"language":[18,51,66],"generation":[19,67],"tasks":[20],"gained":[22],"promising":[23,202],"results":[24,203],"high-resource":[26],"languages":[27,36],"such":[28],"as":[29],"English":[30,120],"the":[33,49,125,152,170,180,186,205],"lesser-resourced":[34],"European":[35],"Italian,":[37],"German,":[38],"Dutch.":[40],"We":[41,184],"investigate":[42],"how":[43],"we":[44,84,131,158],"can":[45],"employ":[46],"DRS":[47,99,102],"low-resource":[50],"Urdu":[52,58,69,81,114,209],"neural":[54,161,196],"(translating":[57],"sentences":[59,70],"into":[60,100],"representations)":[63],"(generating":[68],"from":[71,117,169,221],"representations).":[74],"There":[75],"are":[76],"no":[77],"annotated":[78,129],"corpora":[79],"available,":[82],"so":[83],"adopted":[85],"combined":[87],"approach":[88],"involving":[89],"manual":[91],"annotations":[92],"rule-based":[94],"procedures":[95],"to":[96,179,223,227],"transform":[97],"English-aligned":[98],"Urdu-aligned":[101],"through":[103],"syntactic":[104],"word":[107,111],"surface":[108],"alignment,":[109],"because":[110],"order":[112],"in":[113,142],"(subject\u2013object\u2013verb)":[115],"differs":[116],"that":[118,166,212],"of":[119,127,145,188,208],"(subject\u2013verb\u2013object).":[121],"To":[122],"further":[123],"increase":[124,144],"amount":[126],"semantically":[128],"data,":[130],"developed":[132,159],"lexical,":[133],"grammatical,":[134],"named":[136],"entity-based":[137],"augmentation":[138,191,214],"techniques.":[139],"This":[140],"resulted":[141],"an":[143],"nine":[146],"times":[147],"more":[148,175],"data":[149,172,190,213],"examples.":[150],"Using":[151],"augmented":[153,171],"bank":[155],"Urdu,":[157],"parser":[163],"generator":[165],"benefited":[167],"significantly":[168],"showed":[174],"generalization":[176],"ability":[177],"compared":[178],"model":[181],"without":[182],"augmentation.":[183],"evaluated":[185],"effect":[187],"using":[192],"transformer-based":[194],"state-of-the-art":[195],"sequence-to-sequence":[197],"architecture.":[198],"Our":[199],"implementation":[200],"shows":[201],"processing":[207],"demonstrates":[211],"increases":[215],"performance":[216],"(F1-Score)":[217],"67.12":[222],"76.81,":[224],"leads":[226],"substantially":[228],"increased":[229],"BLEU,":[230],"BERT-Score,":[231],"METEOR,":[232],"ROUGE,":[233],"chrF":[235],"scores":[236],"generation.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}