{"id":"https://openalex.org/W4412888705","doi":"https://doi.org/10.18653/v1/2025.findings-acl.172","title":"Dynamic Prefix as Instructor for Incremental Named Entity Recognition: A Unified Seq2Seq Generation Framework","display_name":"Dynamic Prefix as Instructor for Incremental Named Entity Recognition: A Unified Seq2Seq Generation Framework","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888705","doi":"https://doi.org/10.18653/v1/2025.findings-acl.172"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.172","pdf_url":"https://aclanthology.org/2025.findings-acl.172.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.172.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111169017","display_name":"Zihao Wu","orcid":"https://orcid.org/0009-0003-1289-4144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"YongXiang Hua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YongXiang Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768238","display_name":"Yongxin Zhu","orcid":"https://orcid.org/0000-0002-4757-543X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongxin Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091917332","display_name":"Fang Zhang","orcid":"https://orcid.org/0000-0003-0636-8132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101859765","display_name":"Linli Xu","orcid":"https://orcid.org/0000-0001-6004-4425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linli Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14429416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3294","last_page":"3306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9869999885559082,"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/prefix","display_name":"Prefix","score":0.8625131845474243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949832677841187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5538288354873657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4433678984642029},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22311526536941528}],"concepts":[{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.8625131845474243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949832677841187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5538288354873657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4433678984642029},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22311526536941528},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.172","pdf_url":"https://aclanthology.org/2025.findings-acl.172.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.172","pdf_url":"https://aclanthology.org/2025.findings-acl.172.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G544562989","display_name":null,"funder_award_id":"62276245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888705.pdf","grobid_xml":"https://content.openalex.org/works/W4412888705.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2142481367","https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2385527937","https://openalex.org/W2005880840","https://openalex.org/W2507465767","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"Incremental":[1],"Named":[2],"Entity":[3],"Recognition":[4],"(INER)":[5],"task":[6,69,83],"aims":[7],"to":[8,12,24,27,36,47,86,99,133,159],"update":[9],"a":[10,65,72,82,115,125,129],"model":[11],"extract":[13],"entities":[14,101],"from":[15,40],"an":[16],"expanding":[17],"set":[18],"of":[19,50],"entity":[20,57,172],"type":[21],"candidates":[22],"due":[23],"concerns":[25],"related":[26],"data":[28],"privacy":[29],"and":[30,70,128,139],"scarcity.However,":[31],"conventional":[32],"sequence":[33],"labeling":[34],"approaches":[35],"INER":[37,63],"often":[38],"suffer":[39],"the":[41,48,51,78,88],"catastrophic":[42],"forgetting":[43],"problem,":[44],"which":[45],"leads":[46],"degradation":[49],"model's":[52],"performance":[53,168],"on":[54,144,169],"previously":[55,170],"encountered":[56],"types.In":[58],"this":[59],"paper,":[60],"we":[61,113,148],"formalize":[62],"as":[64,81],"unified":[66],"seq2seq":[67],"generation":[68],"propose":[71],"parameter-efficient":[73],"dynamic":[74],"prefix":[75],"method.By":[76],"employing":[77],"Dynamic":[79],"Prefix":[80],"Instructor":[84],"(DPI)":[85],"guide":[87],"generative":[89,116],"model,":[90],"our":[91,151],"approach":[92,152],"can":[93],"preserve":[94],"taskinvariant":[95],"knowledge":[96],"while":[97,165],"adapting":[98],"new":[100],"with":[102,120],"minimal":[103],"parameter":[104],"updates,":[105],"making":[106],"it":[107],"particularly":[108],"effective":[109],"in":[110,162],"low-resource":[111,163],"scenarios.Additionally,":[112],"introduce":[114],"label":[117],"augmentation":[118],"strategy":[119],"dual":[121],"optimization":[122],"objectives":[123],"including":[124],"self-entropy":[126],"loss":[127,132],"task-aware":[130],"similarity":[131],"enable":[134],"optimal":[135],"balance":[136],"between":[137],"stability":[138],"plasticity.Through":[140],"extensive":[141],"empirical":[142],"evaluation":[143],"standard":[145],"NER":[146],"benchmarks,":[147],"demonstrate":[149],"that":[150],"significantly":[153],"outperforms":[154],"existing":[155],"methods,":[156],"achieving":[157],"up":[158],"13.6%":[160],"improvement":[161],"scenarios":[164],"maintaining":[166],"strong":[167],"learned":[171],"types.":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}