{"id":"https://openalex.org/W4389523880","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.18","title":"Data Pruning for Efficient Model Pruning in Neural Machine Translation","display_name":"Data Pruning for Efficient Model Pruning in Neural Machine Translation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389523880","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.18"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.18","pdf_url":"https://aclanthology.org/2023.findings-emnlp.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.18.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018911648","display_name":"Abdul Hameed Azeemi","orcid":"https://orcid.org/0000-0003-0506-8365"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Abdul Azeemi","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079017254","display_name":"Ihsan Ayyub Qazi","orcid":"https://orcid.org/0000-0002-2262-0353"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ihsan Qazi","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038004767","display_name":"Agha Ali Raza","orcid":"https://orcid.org/0000-0003-0124-9783"},"institutions":[{"id":"https://openalex.org/I207789805","display_name":"Lahore University of Management Sciences","ror":"https://ror.org/05b5x4a35","country_code":"PK","type":"education","lineage":["https://openalex.org/I207789805"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Agha Raza","raw_affiliation_strings":["Lahore University of Management Sciences"],"affiliations":[{"raw_affiliation_string":"Lahore University of Management Sciences","institution_ids":["https://openalex.org/I207789805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018911648"],"corresponding_institution_ids":["https://openalex.org/I207789805"],"apc_list":null,"apc_paid":null,"fwci":0.1751,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5857997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"246"},"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7983933687210083},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7437885999679565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6335911750793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6233311891555786},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5025815963745117},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4873731732368469},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4740985333919525},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43508023023605347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983933687210083},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7437885999679565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6335911750793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6233311891555786},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5025815963745117},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4873731732368469},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4740985333919525},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43508023023605347},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.18","pdf_url":"https://aclanthology.org/2023.findings-emnlp.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.18","pdf_url":"https://aclanthology.org/2023.findings-emnlp.18.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389523880.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2117278770","https://openalex.org/W2257408573","https://openalex.org/W2512924740","https://openalex.org/W2764043458","https://openalex.org/W2915589364","https://openalex.org/W2951013084","https://openalex.org/W2951065878","https://openalex.org/W2963281280","https://openalex.org/W2963341956","https://openalex.org/W2964099985","https://openalex.org/W2964247056","https://openalex.org/W2970686691","https://openalex.org/W2980282514","https://openalex.org/W3006986403","https://openalex.org/W3034999214","https://openalex.org/W3082675885","https://openalex.org/W3101889167","https://openalex.org/W3103649165","https://openalex.org/W3104263050","https://openalex.org/W3119872155","https://openalex.org/W3120459072","https://openalex.org/W3135865967","https://openalex.org/W3172363922","https://openalex.org/W3174481471","https://openalex.org/W3175505246","https://openalex.org/W3180672483","https://openalex.org/W3203385474","https://openalex.org/W4206634569","https://openalex.org/W4226270059","https://openalex.org/W4226354047","https://openalex.org/W4281644279","https://openalex.org/W4283761305","https://openalex.org/W4286511705","https://openalex.org/W4287077733","https://openalex.org/W4287777801","https://openalex.org/W4288089799","https://openalex.org/W4297841840","https://openalex.org/W4322800759","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581"],"abstract_inverted_index":{"Model":[0],"pruning":[1,19,28,39,42,56,68,95,102,134,147],"methods":[2],"reduce":[3],"memory":[4],"requirements":[5],"and":[6,27,78,80,110,135,145],"inference":[7],"time":[8,113],"of":[9,62,73,114,122,129,151],"large-scale":[10],"pre-trained":[11],"language":[12],"models":[13],"after":[14],"deployment.":[15],"However,":[16],"the":[17,30,71,104,111,127,141,149],"actual":[18],"procedure":[20],"is":[21,33],"computationally":[22],"intensive,":[23],"involving":[24],"repeated":[25],"training":[26,64,89,112,130],"until":[29],"required":[31,107],"sparsity":[32],"achieved.":[34],"This":[35],"paper":[36],"combines":[37],"data":[38,101,131,144],"with":[40],"movement":[41,115,133],"for":[43,108],"Neural":[44],"Machine":[45],"Translation":[46],"(NMT)":[47],"to":[48,124,139],"enable":[49],"efficient":[50],"fine-pruning.":[51],"We":[52,66,97],"design":[53],"a":[54,120],"dataset":[55,94],"strategy":[57],"by":[58],"leveraging":[59],"cross-entropy":[60,90],"scores":[61,91],"individual":[63],"instances.":[65],"conduct":[67],"experiments":[69,123],"on":[70,88],"task":[72],"machine":[74],"translation":[75],"from":[76],"Romanian-to-English":[77],"Turkish-to-English,":[79],"demonstrate":[81,99],"that":[82,100],"selecting":[83],"hard-to-learn":[84],"examples":[85],"(top-k)":[86],"based":[87],"outperforms":[92],"other":[93],"methods.":[96],"empirically":[98],"reduces":[103],"overall":[105],"steps":[106],"convergence":[109],"pruning.":[116],"Finally,":[117],"we":[118],"perform":[119],"series":[121],"tease":[125],"apart":[126],"role":[128],"during":[132],"uncover":[136],"new":[137],"insights":[138],"understand":[140],"interplay":[142],"between":[143],"model":[146],"in":[148],"context":[150],"NMT.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}