{"id":"https://openalex.org/W3138392969","doi":"https://doi.org/10.18653/v1/2021.naacl-main.168","title":"Are NLP Models really able to Solve Simple Math Word Problems?","display_name":"Are NLP Models really able to Solve Simple Math Word Problems?","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3138392969","doi":"https://doi.org/10.18653/v1/2021.naacl-main.168","mag":"3138392969"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.naacl-main.168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.168","pdf_url":"https://aclanthology.org/2021.naacl-main.168.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.naacl-main.168.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015473787","display_name":"Arkil Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arkil Patel","raw_affiliation_strings":["Microsoft Research India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067127146","display_name":"Satwik Bhattamishra","orcid":"https://orcid.org/0000-0002-8985-3709"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Satwik Bhattamishra","raw_affiliation_strings":["Microsoft Research India","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029531416","display_name":"Navin Goyal","orcid":"https://orcid.org/0000-0002-8521-0108"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Navin Goyal","raw_affiliation_strings":["Microsoft Research India","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015473787"],"corresponding_institution_ids":["https://openalex.org/I4210124949"],"apc_list":null,"apc_paid":null,"fwci":8.60731808,"has_fulltext":true,"cited_by_count":66,"citation_normalized_percentile":{"value":0.98022839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2080","last_page":"2094"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9990000128746033,"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/T10260","display_name":"Software Engineering Research","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.865609884262085},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.826530396938324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7195266485214233},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7015020251274109},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6680299639701843},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.4770830571651459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45378467440605164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4164072573184967},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4119996130466461},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40484312176704407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1940689980983734}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.865609884262085},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.826530396938324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195266485214233},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7015020251274109},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6680299639701843},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4770830571651459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45378467440605164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4164072573184967},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4119996130466461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40484312176704407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1940689980983734},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2021.naacl-main.168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.168","pdf_url":"https://aclanthology.org/2021.naacl-main.168.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.07191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.07191","pdf_url":"https://arxiv.org/pdf/2103.07191","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":"","raw_type":"text"},{"id":"mag:3138392969","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.07191.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.07191","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.07191","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.naacl-main.168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.naacl-main.168","pdf_url":"https://aclanthology.org/2021.naacl-main.168.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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3138392969.pdf","grobid_xml":"https://content.openalex.org/works/W3138392969.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2475046758","https://openalex.org/W2513499049","https://openalex.org/W2739505524","https://openalex.org/W2740314591","https://openalex.org/W2757276219","https://openalex.org/W2758343314","https://openalex.org/W2906152891","https://openalex.org/W2951286828","https://openalex.org/W2951939640","https://openalex.org/W2962736243","https://openalex.org/W2962843521","https://openalex.org/W2962927633","https://openalex.org/W2963403868","https://openalex.org/W2963779892","https://openalex.org/W2964710271","https://openalex.org/W2965373594","https://openalex.org/W2970726176","https://openalex.org/W3034643750","https://openalex.org/W3034850762","https://openalex.org/W3035267217","https://openalex.org/W3035507081","https://openalex.org/W3101902264","https://openalex.org/W3102315106"],"related_works":["https://openalex.org/W3170403598","https://openalex.org/W2810038208","https://openalex.org/W2968026666","https://openalex.org/W3134642945","https://openalex.org/W3192754120","https://openalex.org/W3131994959","https://openalex.org/W3158186660","https://openalex.org/W2460866764","https://openalex.org/W2092993939","https://openalex.org/W3213368902","https://openalex.org/W1743028195","https://openalex.org/W2964345707","https://openalex.org/W304768798","https://openalex.org/W2287873998","https://openalex.org/W145815032","https://openalex.org/W2971418718","https://openalex.org/W3128392690","https://openalex.org/W3034519970","https://openalex.org/W2951863880","https://openalex.org/W3152764928"],"abstract_inverted_index":{"The":[0,156],"problem":[1],"of":[2,51,122,180],"designing":[3],"NLP":[4],"solvers":[5,25,83,103],"for":[6,33,177],"math":[7],"word":[8,40],"problems":[9,43],"(MWP)":[10],"has":[11],"seen":[12],"sustained":[13],"research":[14,52],"activity":[15],"and":[16,73],"steady":[17],"gains":[18],"in":[19,70,113],"the":[20,30,49,80,93,110,114,178,181],"test":[21],"accuracy.":[22,136],"Since":[23],"existing":[24,81,154],"achieve":[26,89,133],"high":[27,90,135],"performance":[28,91],"on":[29,85,92,166],"benchmark":[31,94],"datasets":[32],"elementary":[34],"level":[35],"MWPs":[36,68,128],"containing":[37],"one-unknown":[38],"arithmetic":[39],"problems,":[41],"such":[42],"are":[44],"often":[45],"considered":[46],"\"solved\"":[47],"with":[48],"bulk":[50],"attention":[53,65],"moving":[54],"to":[55,66,88,109,173],"more":[56],"complex":[57],"MWPs.":[58,123,182],"In":[59],"this":[60,97],"paper,":[61],"we":[62,99,138],"restrict":[63],"our":[64],"English":[67],"taught":[69],"grades":[71],"four":[72],"lower.":[74],"We":[75],"provide":[76],"strong":[77],"evidence":[78],"that":[79,101,104,126,170],"MWP":[82,102,115],"rely":[84],"shallow":[86],"heuristics":[87],"datasets.":[95,155],"To":[96],"end,":[98],"show":[100],"do":[105],"not":[106],"have":[107],"access":[108],"question":[111],"asked":[112],"can":[116,131],"still":[117],"solve":[118],"a":[119,140],"large":[120],"fraction":[121],"Similarly,":[124],"models":[125,162],"treat":[127],"as":[129],"bag-of-words":[130],"also":[132],"surprisingly":[134],"Further,":[137],"introduce":[139],"challenge":[141],"dataset,":[142],"SVAMP,":[143,167],"created":[144],"by":[145,160],"applying":[146],"carefully":[147],"chosen":[148],"variations":[149],"over":[150],"examples":[151],"sampled":[152],"from":[153],"best":[157],"accuracy":[158],"achieved":[159],"state-of-the-art":[161],"is":[163],"substantially":[164],"lower":[165],"thus":[168],"showing":[169],"much":[171],"remains":[172],"be":[174],"done":[175],"even":[176],"simplest":[179]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}