{"id":"https://openalex.org/W2804713279","doi":"https://doi.org/10.18653/v1/p18-1196","title":"Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers","display_name":"Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2804713279","doi":"https://doi.org/10.18653/v1/p18-1196","mag":"2804713279"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1196","pdf_url":"https://www.aclweb.org/anthology/P18-1196.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1196.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Georgios Spithourakis","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Georgios Spithourakis","raw_affiliation_strings":["Department of Computer Science University College London"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sebastian Riedel","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Riedel","raw_affiliation_strings":["Department of Computer Science University College London"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":1.523,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.86929028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2104","last_page":"2115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9979000091552734,"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":0.9973999857902527,"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/numeral-system","display_name":"Numeral system","score":0.7875000238418579},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6064000129699707},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6018999814987183},{"id":"https://openalex.org/keywords/numeracy","display_name":"Numeracy","score":0.59170001745224},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.4666000008583069},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41429999470710754}],"concepts":[{"id":"https://openalex.org/C204160518","wikidata":"https://www.wikidata.org/wiki/Q122653","display_name":"Numeral system","level":2,"score":0.7875000238418579},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C53537400","wikidata":"https://www.wikidata.org/wiki/Q140637","display_name":"Numeracy","level":3,"score":0.59170001745224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5536999702453613},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.4666000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33070001006126404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p18-1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1196","pdf_url":"https://www.aclweb.org/anthology/P18-1196.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.08154","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.08154","pdf_url":"https://arxiv.org/pdf/1805.08154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1196","pdf_url":"https://www.aclweb.org/anthology/P18-1196.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804713279.pdf","grobid_xml":"https://content.openalex.org/works/W2804713279.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Numeracy":[0],"is":[1,11,139,145],"the":[2,88,129],"ability":[3],"to":[4,59,78,128,151,157],"understand":[5],"and":[6,17,23,43,46,70,94,124],"work":[7],"with":[8,37],"numbers.":[9],"It":[10],"a":[12,48,54,84,165],"necessary":[13],"skill":[14],"for":[15,34,133],"composing":[16],"understanding":[18],"documents":[19],"in":[20,126],"clinical,":[21],"scientific,":[22],"other":[24,158],"technical":[25],"domains.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"explore":[31],"different":[32],"strategies":[33,106],"modelling":[35,153],"numerals":[36,61,80,91,155],"language":[38,152],"models,":[39],"such":[40],"as":[41],"memorisation":[42],"digit-by-digit":[44],"composition,":[45],"propose":[47],"novel":[49],"neural":[50],"architecture":[51],"that":[52,74],"uses":[53],"continuous":[55,112],"probability":[56,113],"density":[57,114],"function":[58,115],"model":[60,116],"from":[62,81],"an":[63],"open":[64],"vocabulary.":[65,167],"Our":[66,111],"evaluation":[67],"on":[68,87],"clinical":[69],"scientific":[71],"datasets":[72],"shows":[73],"using":[75,161],"hierarchical":[76],"models":[77],"distinguish":[79],"words":[82],"improves":[83],"perplexity":[85],"metric":[86],"subset":[89],"of":[90,97,105],"by":[92,122],"2":[93],"4":[95],"orders":[96],"magnitude,":[98],"respectively,":[99],"over":[100,164],"nonhierarchical":[101],"models.":[102],"A":[103],"combination":[104],"can":[107],"further":[108],"improve":[109],"perplexity.":[110],"reduces":[117],"mean":[118],"absolute":[119],"percentage":[120],"errors":[121],"18%":[123],"54%":[125],"comparison":[127],"second":[130],"best":[131],"strategy":[132],"each":[134],"dataset,":[135],"respectively.":[136],"'John's":[137,143],"height":[138,144],"1.75":[140],"metres'":[141,147],"(realistic)":[142],"999.999":[146],"(unrealistic)":[148],"Existing":[149],"approaches":[150],"treat":[154],"similarly":[156],"words,":[159],"typically":[160],"categorical":[162],"distributions":[163],"fixed":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2018-06-01T00:00:00"}