{"id":"https://openalex.org/W7126417984","doi":"https://doi.org/10.18653/v1/2022.wmt-1.80","title":"Too Brittle to Touch: Comparing the Stability of Quantization and Distillation towards Developing Low-Resource MT Models","display_name":"Too Brittle to Touch: Comparing the Stability of Quantization and Distillation towards Developing Low-Resource MT Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W7126417984","doi":"https://doi.org/10.18653/v1/2022.wmt-1.80"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2022.wmt-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.80","pdf_url":"https://aclanthology.org/2022.wmt-1.80.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":"Proceedings of the Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.wmt-1.80.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124473644","display_name":"Harshita Diddee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harshita Diddee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006779728","display_name":"Sandipan Dandapat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandipan Dandapat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124534211","display_name":"Monojit Choudhury","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124608450","display_name":"Tanuja Ganu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanuja Ganu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124635255","display_name":"Kalika Bali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kalika Bali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29837518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"870","last_page":"885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.030500000342726707,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.030500000342726707,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T13126","display_name":"Scientific Research and Discoveries","score":0.012400000356137753,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.40700000524520874},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.3968999981880188},{"id":"https://openalex.org/keywords/brittleness","display_name":"Brittleness","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41269999742507935},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C136478896","wikidata":"https://www.wikidata.org/wiki/Q898288","display_name":"Brittleness","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3813999891281128},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.329800009727478},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C154030694","wikidata":"https://www.wikidata.org/wiki/Q1436074","display_name":"Fractionating column","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2635999917984009},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.wmt-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.80","pdf_url":"https://aclanthology.org/2022.wmt-1.80.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":"Proceedings of the Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wmt-1.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wmt-1.80","pdf_url":"https://aclanthology.org/2022.wmt-1.80.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":"Proceedings of the Seventh Conference on Machine Translation (WMT)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126417984.pdf","grobid_xml":"https://content.openalex.org/works/W7126417984.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Leveraging":[0],"shared":[1],"learning":[2],"through":[3],"Massively":[4],"Multilingual":[5],"Models,":[6],"state-of-the-art":[7],"machine":[8],"translation":[9],"(MT)":[10],"models":[11,34,61,87],"are":[12,36],"often":[13],"able":[14],"to":[15,17,45,58,89],"adapt":[16],"the":[18,29,79,82,85,95,103,111,124,130,153,159],"paucity":[19],"of":[20,31,84,97,110,126,132,156],"data":[21,99],"for":[22,101,129,152],"low-resource":[23,144],"languages.However,":[24],"this":[25,51],"performance":[26,83,150],"comes":[27],"at":[28],"cost":[30],"significantly":[32],"bloated":[33],"which":[35],"not":[37],"practically":[38],"deployable.Knowledge":[39],"Distillation":[40],"is":[41],"one":[42],"popular":[43],"technique":[44],"develop":[46],"competitive":[47],"lightweight":[48],"models:":[49],"In":[50],"work,":[52],"we":[53,76,122,135],"first":[54],"evaluate":[55],"it's":[56],"use":[57,125],"compress":[59],"MT":[60],"focusing":[62],"specifically":[63],"on":[64,92],"languages":[65,161],"with":[66],"extremely":[67],"limited":[68],"training":[69,106],"data.Through":[70],"our":[71,163],"analysis":[72],"across":[73,142],"8":[74],"languages,":[75,145,157],"find":[77,136],"that":[78,137],"variance":[80],"in":[81,162],"distilled":[86],"due":[88],"their":[90],"dependence":[91],"priors":[93],"including":[94],"amount":[96],"synthetic":[98],"used":[100],"distillation,":[102],"student":[104],"architecture,":[105],"hyper-parameters":[107],"and":[108],"confidence":[109],"teacher":[112],"models,":[113],"makes":[114],"distillation":[115,139],"a":[116],"brittle":[117],"compression":[118,131],"mechanism.To":[119],"mitigate":[120],"this,":[121],"explore":[123],"post-training":[127],"quantization":[128,146],"these":[133],"models.Here,":[134],"while":[138],"provides":[140,147],"gains":[141],"some":[143],"more":[148],"consistent":[149],"trends":[151],"entire":[154],"range":[155],"especially":[158],"lowestresource":[160],"target":[164],"set.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-02T00:00:00"}