{"id":"https://openalex.org/W3213147052","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.557","title":"Numeracy enhances the Literacy of Language Models","display_name":"Numeracy enhances the Literacy of Language Models","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3213147052","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.557","mag":"3213147052"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.557","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.557","pdf_url":"https://aclanthology.org/2021.emnlp-main.557.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.557.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008902336","display_name":"Avijit Thawani","orcid":"https://orcid.org/0000-0002-4289-3607"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avijit Thawani","raw_affiliation_strings":["University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073443117","display_name":"Jay Pujara","orcid":"https://orcid.org/0000-0001-6921-1744"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Pujara","raw_affiliation_strings":["University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008608420","display_name":"Filip Ilievski","orcid":"https://orcid.org/0000-0002-1735-0686"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Filip Ilievski","raw_affiliation_strings":["University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California / Los Angeles Information Sciences Institute / Marina del Rey","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1268,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36654344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6960","last_page":"6967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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":0.9814000129699707,"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/numeracy","display_name":"Numeracy","score":0.9103515148162842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6698235273361206},{"id":"https://openalex.org/keywords/literacy","display_name":"Literacy","score":0.6574988961219788},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6368389129638672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5794905424118042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5632606744766235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5323482155799866},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5012040138244629},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4917459785938263},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4905954897403717},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48781540989875793},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43579694628715515},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3591821789741516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3137018084526062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18564969301223755}],"concepts":[{"id":"https://openalex.org/C53537400","wikidata":"https://www.wikidata.org/wiki/Q140637","display_name":"Numeracy","level":3,"score":0.9103515148162842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6698235273361206},{"id":"https://openalex.org/C547764534","wikidata":"https://www.wikidata.org/wiki/Q8236","display_name":"Literacy","level":2,"score":0.6574988961219788},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6368389129638672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5794905424118042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5632606744766235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5323482155799866},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5012040138244629},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4917459785938263},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4905954897403717},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48781540989875793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43579694628715515},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3591821789741516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3137018084526062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18564969301223755},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.557","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.557","pdf_url":"https://aclanthology.org/2021.emnlp-main.557.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"mag:3213147052","is_oa":false,"landing_page_url":"https://aclanthology.org/2021.emnlp-main.557/","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.557","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.557","pdf_url":"https://aclanthology.org/2021.emnlp-main.557.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3213147052.pdf","grobid_xml":"https://content.openalex.org/works/W3213147052.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W204967857","https://openalex.org/W2004286722","https://openalex.org/W2121879602","https://openalex.org/W2950744025","https://openalex.org/W2962817854","https://openalex.org/W2963341956","https://openalex.org/W2986266667","https://openalex.org/W3034602344","https://openalex.org/W3035428952","https://openalex.org/W3090254696","https://openalex.org/W3098824823","https://openalex.org/W3100778284","https://openalex.org/W3102199783","https://openalex.org/W3105643199","https://openalex.org/W3166890286"],"related_works":["https://openalex.org/W2976956516","https://openalex.org/W3196833733","https://openalex.org/W3040010296","https://openalex.org/W2907849599","https://openalex.org/W2549793564","https://openalex.org/W2558744183","https://openalex.org/W106247045","https://openalex.org/W3203017269","https://openalex.org/W2624616057","https://openalex.org/W2885361267","https://openalex.org/W2964307221","https://openalex.org/W3034837209","https://openalex.org/W2891077740","https://openalex.org/W2805533746","https://openalex.org/W2168129428","https://openalex.org/W2888881387","https://openalex.org/W2915511574","https://openalex.org/W2901983194","https://openalex.org/W3171707904","https://openalex.org/W2250925555"],"abstract_inverted_index":{"Specialized":[0],"number":[1,18,68,106,125],"representations":[2],"in":[3,38,113,132],"NLP":[4],"have":[5],"shown":[6],"improvements":[7],"on":[8,70],"numerical":[9],"reasoning":[10],"tasks":[11],"like":[12],"arithmetic":[13],"word":[14,75],"problems":[15],"and":[16,57,98,104,139],"masked":[17,74],"prediction.":[19],"But":[20],"humans":[21],"also":[22,145],"use":[23],"numeracy":[24],"to":[25,100,147],"make":[26],"better":[27,46],"sense":[28],"of":[29,48,54,64,73],"world":[30],"concepts,":[31],"e.g.,":[32],"you":[33],"can":[34],"seat":[35],"5":[36],"people":[37],"your":[39],"room":[40],"but":[41],"not":[42],"500.":[43],"Does":[44],"a":[45,51,79,91,110,136],"grasp":[47],"numbers":[49,97],"improve":[50],"model's":[52],"understanding":[53],"other":[55],"concepts":[56],"words?":[58],"This":[59],"paper":[60],"studies":[61],"the":[62,71,123],"effect":[63],"using":[65],"six":[66],"different":[67],"encoders":[69],"task":[72],"prediction":[76,133],"(MWP),":[77],"as":[78],"proxy":[80],"for":[81,115],"evaluating":[82],"literacy.":[83],"To":[84],"support":[85],"this":[86],"investigation,":[87],"we":[88],"develop":[89],"Wiki-Convert,":[90],"900,000":[92],"sentence":[93],"dataset":[94],"annotated":[95,150],"with":[96],"units,":[99],"avoid":[101],"conflating":[102],"nominal":[103],"ordinal":[105],"occurrences.":[107],"We":[108,152],"find":[109],"significant":[111],"improvement":[112],"MWP":[114],"sentences":[116],"containing":[117],"numbers,":[118],"that":[119,140],"exponent":[120],"embeddings":[121],"are":[122],"best":[124],"encoders,":[126],"yielding":[127],"over":[128,135],"2":[129],"points":[130],"jump":[131],"accuracy":[134],"BERT":[137],"baseline,":[138],"these":[141],"enhanced":[142],"literacy":[143],"skills":[144],"generalize":[146],"contexts":[148],"without":[149],"numbers.":[151],"release":[153],"all":[154],"code":[155],"at":[156],"https://git.io/JuZXn.":[157]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}