{"id":"https://openalex.org/W7166878155","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1127","title":"E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition","display_name":"E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166878155","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1127"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1127","pdf_url":"https://aclanthology.org/2026.findings-acl.1127.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1127.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139769749","display_name":"Meng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139841824","display_name":"Jinzhong Ning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinzhong Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139739239","display_name":"Xiaolong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139816904","display_name":"Hongfei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139741964","display_name":"Yijia Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijia Zhang","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":0.86599638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22460","last_page":"22469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8562999963760376,"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":0.8562999963760376,"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":0.0706000030040741,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.015599999576807022,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.3856000006198883},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3352000117301941},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.32829999923706055},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3052000105381012},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2890999913215637},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.2727999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110999941825867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4643000066280365},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1127","pdf_url":"https://aclanthology.org/2026.findings-acl.1127.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1127","pdf_url":"https://aclanthology.org/2026.findings-acl.1127.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8348406856","display_name":null,"funder_award_id":"62506058","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"},{"id":"https://openalex.org/F4320331088","display_name":"Natural Science Foundation for Young Scientists of Shanxi Province","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166878155.pdf","grobid_xml":"https://content.openalex.org/works/W7166878155.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Grounded":[0],"Multimodal":[1],"Named":[2],"Entity":[3],"Recognition":[4],"(GMNER)":[5],"aims":[6],"to":[7,23,46,94,98,140],"jointly":[8],"identify":[9],"named":[10],"entity":[11,22,40,65],"mentions":[12],"in":[13,28],"text,":[14],"predict":[15],"their":[16],"semantic":[17,67],"types,":[18],"and":[19,42,49,71,90,146,153,177],"ground":[20],"each":[21],"a":[24,58,76],"corresponding":[25],"visual":[26,43,69,102],"region":[27],"an":[29,85],"associated":[30],"image.Existing":[31],"approaches":[32],"predominantly":[33],"adopt":[34],"pipelinebased":[35],"architectures":[36],"that":[37,63,157],"decouple":[38],"textual":[39],"recognition":[41],"grounding,":[44,70],"leading":[45],"error":[47],"accumulation":[48],"suboptimal":[50],"joint":[51],"optimization.In":[52],"this":[53],"paper,":[54],"we":[55,123],"propose":[56],"E2E-GMNER,":[57],"fully":[59],"end-to-end":[60],"generative":[61,119],"framework":[62],"unifies":[64],"recognition,":[66],"typing,":[68],"implicit":[72],"knowledge":[73,106],"reasoning":[74,93],"within":[75],"single":[77],"multimodal":[78],"large":[79],"language":[80],"model.We":[81],"formulate":[82],"GM-NER":[83],"as":[84],"instruction-tuned":[86],"conditional":[87],"generation":[88],"task":[89],"incorporate":[91],"chain-of-thought":[92],"enable":[95],"the":[96,116,151,167,171],"model":[97],"adaptively":[99],"determine":[100],"when":[101],"evidence":[103],"or":[104],"background":[105],"is":[107],"informative,":[108],"reducing":[109],"reliance":[110],"on":[111,150],"noisy":[112],"cues.To":[113],"further":[114],"address":[115],"instability":[117],"of":[118,166,173],"bounding":[120],"box":[121,133],"prediction,":[122],"introduce":[124],"Gaussian":[125],"Risk-Aware":[126],"Box":[127],"Perturbation":[128],"(GRBP),":[129],"which":[130],"replaces":[131],"hard":[132],"supervision":[134],"with":[135,164],"probabilistically":[136],"perturbed":[137],"soft":[138],"targets":[139],"improve":[141],"robustness":[142],"against":[143],"annotation":[144],"noise":[145],"discretization":[147],"errors.Extensive":[148],"experiments":[149],"Twitter-GMNER":[152],"Twitter-FMNERG":[154],"benchmarks":[155],"demonstrate":[156],"E2E-GMNER":[158],"achieves":[159],"highly":[160],"competitive":[161],"performance":[162],"compared":[163],"state":[165],"art":[168],"methods,":[169],"validating":[170],"effectiveness":[172],"unified":[174],"endto-end":[175],"optimization":[176],"noise-aware":[178],"grounding":[179],"supervision.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}