{"id":"https://openalex.org/W4285333916","doi":"https://doi.org/10.1145/3490354.3494412","title":"Pre-training and evaluation of numeracy-oriented language model","display_name":"Pre-training and evaluation of numeracy-oriented language model","publication_year":2021,"publication_date":"2021-11-03","ids":{"openalex":"https://openalex.org/W4285333916","doi":"https://doi.org/10.1145/3490354.3494412"},"language":"en","primary_location":{"id":"doi:10.1145/3490354.3494412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490354.3494412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490354.3494412","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3490354.3494412","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fuli Feng","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036741701","display_name":"Xilin Rui","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Rui","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488072","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0002-1632-7812"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yixin Cao","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051925942"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23084164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9865999817848206,"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":0.9445062875747681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288709878921509},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6126648187637329},{"id":"https://openalex.org/keywords/literacy","display_name":"Literacy","score":0.4946906268596649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4744090735912323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44944360852241516},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4116942286491394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3385707139968872},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.31077998876571655},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08472532033920288}],"concepts":[{"id":"https://openalex.org/C53537400","wikidata":"https://www.wikidata.org/wiki/Q140637","display_name":"Numeracy","level":3,"score":0.9445062875747681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288709878921509},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6126648187637329},{"id":"https://openalex.org/C547764534","wikidata":"https://www.wikidata.org/wiki/Q8236","display_name":"Literacy","level":2,"score":0.4946906268596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4744090735912323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44944360852241516},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4116942286491394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3385707139968872},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31077998876571655},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08472532033920288},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490354.3494412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490354.3494412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490354.3494412","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3490354.3494412","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490354.3494412","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490354.3494412","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285333916.pdf","grobid_xml":"https://content.openalex.org/works/W4285333916.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1539746312","https://openalex.org/W1989085630","https://openalex.org/W2741438349","https://openalex.org/W2804713279","https://openalex.org/W2945127593","https://openalex.org/W2948947170","https://openalex.org/W2950645060","https://openalex.org/W2950744025","https://openalex.org/W2951873305","https://openalex.org/W2954323493","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962817854","https://openalex.org/W2963026768","https://openalex.org/W2963430447","https://openalex.org/W2965968319","https://openalex.org/W2970609357","https://openalex.org/W2970900584","https://openalex.org/W2973111096","https://openalex.org/W2986266667","https://openalex.org/W3021244424","https://openalex.org/W3021397474","https://openalex.org/W3035053871","https://openalex.org/W3099446234","https://openalex.org/W3104467951","https://openalex.org/W3105817677","https://openalex.org/W3156191477","https://openalex.org/W3173223111","https://openalex.org/W3173665834","https://openalex.org/W3174986053"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W4321496520","https://openalex.org/W4323060038","https://openalex.org/W2798669739","https://openalex.org/W4323981018","https://openalex.org/W2790173704","https://openalex.org/W4289299384","https://openalex.org/W2772215414","https://openalex.org/W2984206076","https://openalex.org/W3086845375"],"abstract_inverted_index":{"Pre-trained":[0],"language":[1,13],"model":[2],"(LM)":[3],"has":[4,55],"led":[5],"to":[6,18,25,59,107,126,229],"significant":[7],"performance":[8],"gains":[9],"in":[10,65],"various":[11],"natural":[12],"processing":[14],"(NLP)":[15],"applications":[16,67],"due":[17],"its":[19,142],"strong":[20],"literacy,":[21],"e.g.,":[22],"the":[23,30,48,60,83,101,124,128,136,146,169,195,198,201,208,227],"ability":[24],"capture":[26],"word":[27],"dependencies.":[28],"However,":[29,82],"existing":[31],"pre-trained":[32,63,172,202],"LMs":[33,64],"largely":[34],"ignore":[35],"numeracy,":[36],"i.e.,":[37],"treating":[38],"numbers":[39,133],"within":[40],"text":[41],"as":[42,72],"plain":[43],"words":[44],"and":[45,75,85,130,134,141,157,188,204,217],"without":[46],"understanding":[47,84],"basic":[49],"numerical":[50,105,117],"concepts.":[51],"The":[52],"weak":[53],"numeracy":[54,170],"become":[56],"a":[57,139],"barrier":[58],"use":[61],"of":[62,87,104,132,164,171,180,200],"NLP":[66],"over":[68],"financial":[69,88,165,212],"documents":[70,89,166,213],"such":[71],"annual":[73],"filings":[74],"analyst":[76],"reports":[77],"that":[78,122],"are":[79,90],"number":[80,140,183],"intensive.":[81],"analysis":[86],"becoming":[91],"gradationally":[92],"important.":[93],"To":[94],"bridge":[95],"this":[96,98],"gap,":[97],"work":[99],"explores":[100],"central":[102],"theme":[103],"pre-training":[106,118],"empower":[108],"LM":[109,125,210],"with":[110,120],"numeracy.":[111],"In":[112],"particular,":[113],"we":[114,151,160],"propose":[115],"two":[116,153],"methods":[119,148],"objectives":[121],"encourage":[123],"understand":[127],"magnitude":[129],"value":[131],"encode":[135],"dependency":[137],"between":[138],"context.":[143],"By":[144],"applying":[145],"proposed":[147],"on":[149,176,194,219],"BERT,":[150],"pre-train":[152],"LMs,":[154],"named":[155,224],"BERT-M":[156,203],"BERT-V.":[158],"Moreover,":[159],"construct":[161],"four":[162],"datasets":[163,196],"for":[167,211],"evaluating":[168],"LM,":[173],"which":[174,206],"focus":[175],"three":[177],"fundamental":[178],"perspectives":[179],"numeracy:":[181],"a)":[182],"embedding;":[184],"b)":[185],"number-text":[186],"composition;":[187],"c)":[189],"number-number":[190],"composition.":[191],"Extensive":[192],"experiments":[193],"validate":[197],"effectiveness":[199],"BERT-V,":[205],"outperform":[207],"state-of-the-art":[209],"(FinBERT)":[214],"by":[215],"4.83%":[216],"4.34%":[218],"average.":[220],"Furthermore,":[221],"their":[222],"aggregation":[223],"BERT-MV":[225],"increases":[226],"gain":[228],"10.88%.":[230]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}