{"id":"https://openalex.org/W4385572968","doi":"https://doi.org/10.18653/v1/2022.conll-1.28","title":"Characterizing Verbatim Short-Term Memory in Neural Language Models","display_name":"Characterizing Verbatim Short-Term Memory in Neural Language Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572968","doi":"https://doi.org/10.18653/v1/2022.conll-1.28"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.conll-1.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.conll-1.28","pdf_url":"https://aclanthology.org/2022.conll-1.28.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 26th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2022.conll-1.28.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013188295","display_name":"Kristijan Armeni","orcid":"https://orcid.org/0000-0001-8391-8965"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kristijan Armeni","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098010","display_name":"Christopher Honey","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Honey","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081824828","display_name":"Tal Linzen","orcid":"https://orcid.org/0000-0003-0435-6912"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tal Linzen","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013188295"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.276,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65374633,"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":"405","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8343310952186584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7389031648635864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6735578775405884},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6653172969818115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6614465713500977},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.656451404094696},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5528197884559631},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.5361207723617554},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5071182250976562},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44379109144210815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343310952186584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7389031648635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6735578775405884},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6653172969818115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6614465713500977},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.656451404094696},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5528197884559631},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.5361207723617554},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5071182250976562},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44379109144210815},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.conll-1.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.conll-1.28","pdf_url":"https://aclanthology.org/2022.conll-1.28.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 26th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.conll-1.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.conll-1.28","pdf_url":"https://aclanthology.org/2022.conll-1.28.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 26th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322554","display_name":"Javna Agencija za Raziskovalno Dejavnost RS","ror":"https://ror.org/059bp8k51"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572968.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1602017060","https://openalex.org/W1967852455","https://openalex.org/W2064675550","https://openalex.org/W2066785847","https://openalex.org/W2089217417","https://openalex.org/W2104622689","https://openalex.org/W2133564696","https://openalex.org/W2535697732","https://openalex.org/W2549835527","https://openalex.org/W2786167576","https://openalex.org/W2794687249","https://openalex.org/W2888922637","https://openalex.org/W2921890305","https://openalex.org/W2922523190","https://openalex.org/W2938704169","https://openalex.org/W2963341956","https://openalex.org/W2963751529","https://openalex.org/W2963951265","https://openalex.org/W2964165364","https://openalex.org/W2977551935","https://openalex.org/W2979826702","https://openalex.org/W3001279689","https://openalex.org/W3023662336","https://openalex.org/W3103536442","https://openalex.org/W3159684727","https://openalex.org/W3173681001","https://openalex.org/W4287324987","https://openalex.org/W4287667694","https://openalex.org/W4288089799","https://openalex.org/W4289552613","https://openalex.org/W4292779060","https://openalex.org/W4297412003","https://openalex.org/W4298422451","https://openalex.org/W4299838440","https://openalex.org/W4301152280","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2407160479","https://openalex.org/W3204607391","https://openalex.org/W2546216834","https://openalex.org/W3034520363","https://openalex.org/W3016124757","https://openalex.org/W2339260772","https://openalex.org/W4294174385","https://openalex.org/W4292474994","https://openalex.org/W4287761227","https://openalex.org/W4307415490"],"abstract_inverted_index":{"When":[0],"a":[1,18,49,65,115,183,201],"language":[2,9,32,38,54],"model":[3,121],"is":[4],"trained":[5,113],"to":[6,82,126,147,151,161,182],"predict":[7],"natural":[8],"sequences,":[10],"its":[11],"prediction":[12],"at":[13],"each":[14],"moment":[15],"depends":[16],"on":[17,114,132],"representation":[19],"of":[20,25,67,97,164,208],"prior":[21,29,128,209],"context.":[22],"What":[23],"kind":[24],"information":[26],"about":[27],"the":[28,42,75,80,83,89,93,100,104,138,162,170,198,213],"context":[30],"can":[31],"models":[33,39,55],"retrieve?":[34],"We":[35,71,86,175],"tested":[36],"whether":[37],"could":[40,188],"retrieve":[41,190],"exact":[43],"words":[44],"that":[45,88,177,187],"occurred":[46,69],"previously":[47],"in":[48,63,77],"text.":[50],"In":[51,136],"our":[52],"paradigm,":[53],"(transformers":[56],"and":[57,95,118,150,166,203],"an":[58],"LSTM)":[59],"processed":[60],"English":[61],"text":[62],"which":[64,144],"list":[66,171],"nouns":[68,98,165],"twice.":[70],"operationalized":[72],"retrieval":[73,106,157],"as":[74],"reduction":[76],"surprisal":[78],"from":[79,99],"first":[81,101],"second":[84],"list.":[85,102],"found":[87],"transformers":[90,178],"retrieved":[91],"both":[92],"identity":[94],"ordering":[96],"Further,":[103],"transformers'":[105],"was":[107,130,145,158,172],"markedly":[108],"enhanced":[109],"when":[110,169],"they":[111],"were":[112],"larger":[116],"corpus":[117],"with":[119],"greater":[120],"depth.":[122],"Lastly,":[123],"their":[124],"ability":[125],"index":[127],"tokens":[129,149],"dependent":[131],"learned":[133],"attention":[134],"patterns.":[135],"contrast,":[137],"LSTM":[139,199],"exhibited":[140],"less":[141],"precise":[142],"retrieval,":[143],"limited":[146],"list-initial":[148],"short":[152],"intervening":[153],"texts.":[154],"The":[155],"LSTM's":[156],"not":[159],"sensitive":[160],"order":[163],"it":[167],"improved":[168],"semantically":[173],"coherent.":[174],"conclude":[176],"implemented":[179],"something":[180],"akin":[181],"working":[184],"memory":[185],"system":[186],"flexibly":[189],"individual":[191],"token":[192],"representations":[193],"across":[194],"arbitrary":[195],"delays;":[196],"conversely,":[197],"maintained":[200],"coarser":[202],"more":[204],"rapidly-decaying":[205],"semantic":[206],"gist":[207],"tokens,":[210],"weighted":[211],"toward":[212],"earliest":[214],"items.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}