{"id":"https://openalex.org/W7126372634","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.57","title":"Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling","display_name":"Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126372634","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.57"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.57","pdf_url":"https://aclanthology.org/2024.findings-eacl.57.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.57.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124550839","display_name":"Qingyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingyang Wu","raw_affiliation_strings":["Columbia University Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124476630","display_name":"Zhou Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Columbia University Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56926845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"853","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7994999885559082,"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/T12031","display_name":"Speech and dialogue systems","score":0.7994999885559082,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.029100000858306885,"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":0.026900000870227814,"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/stateful-firewall","display_name":"Stateful firewall","score":0.6444000005722046},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.35920000076293945},{"id":"https://openalex.org/keywords/stateless-protocol","display_name":"Stateless protocol","score":0.22470000386238098},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.2126999944448471}],"concepts":[{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.6444000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291999816894531},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25679999589920044},{"id":"https://openalex.org/C103613024","wikidata":"https://www.wikidata.org/wiki/Q230924","display_name":"Stateless protocol","level":3,"score":0.22470000386238098},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2126999944448471},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.21119999885559082},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.20659999549388885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19629999995231628},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1956000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.57","pdf_url":"https://aclanthology.org/2024.findings-eacl.57.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.57","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.57","pdf_url":"https://aclanthology.org/2024.findings-eacl.57.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126372634.pdf","grobid_xml":"https://content.openalex.org/works/W7126372634.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformer":[0,105],"models":[1,40],"have":[2],"achieved":[3,96],"great":[4],"performance":[5,100],"in":[6],"dialogue":[7,15,47,83],"generation":[8],"tasks.However,":[9],"their":[10],"inability":[11],"to":[12,19,102],"process":[13],"long":[14],"history":[16,48],"often":[17],"leads":[18],"truncation":[20],"of":[21,45,78],"the":[22,46,58,67,71,76],"context.To":[23],"address":[24],"this":[25],"problem,":[26],"we":[27],"propose":[28],"a":[29,53],"novel":[30],"memory-augmented":[31],"transformer":[32],"that":[33,92],"is":[34],"compatible":[35],"with":[36],"existing":[37],"pre-trained":[38,59,104],"encoder-decoder":[39],"and":[41,70,85,99],"enables":[42],"efficient":[43],"preservation":[44],"information.The":[49],"new":[50],"model":[51,80],"incorporates":[52],"separate":[54],"memory":[55,68],"module":[56],"alongside":[57],"transformer,":[60],"which":[61],"can":[62],"effectively":[63],"interchange":[64],"information":[65],"between":[66],"states":[69],"current":[72],"input":[73],"context.We":[74],"evaluate":[75],"efficiency":[77,98],"our":[79,93],"on":[81],"three":[82],"datasets":[84],"two":[86],"language":[87],"modeling":[88],"datasets.Experimental":[89],"results":[90],"show":[91],"method":[94],"has":[95],"superior":[97],"compared":[101],"other":[103],"baselines.":[106]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-02T00:00:00"}