{"id":"https://openalex.org/W4416078647","doi":"https://doi.org/10.1145/3746252.3761051","title":"Exploring Iterative Refinement for Nested Named Entity Recognition with IoU-aware Denoising Diffusion","display_name":"Exploring Iterative Refinement for Nested Named Entity Recognition with IoU-aware Denoising Diffusion","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078647","doi":"https://doi.org/10.1145/3746252.3761051"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761051","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049898836","display_name":"Qiaoxuan Yin","orcid":"https://orcid.org/0009-0000-1036-6573"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiaoxuan Yin","raw_affiliation_strings":["School of Computer Science, Xiangtan University, Xiangtan, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xiangtan University, Xiangtan, Hunan, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717467","display_name":"Jianquan Ouyang","orcid":"https://orcid.org/0000-0002-7518-5156"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianquan Ouyang","raw_affiliation_strings":["School of Computer Science, Xiangtan University, Xiangtan, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xiangtan University, Xiangtan, Hunan, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"last","author":{"id":null,"display_name":"Huanrong Tang","orcid":"https://orcid.org/0000-0003-2484-9124"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanrong Tang","raw_affiliation_strings":["School of Computer Science, Xiangtan University, Xiangtan, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xiangtan University, Xiangtan, Hunan, China","institution_ids":["https://openalex.org/I4610292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049898836"],"corresponding_institution_ids":["https://openalex.org/I4610292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18649293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3888","last_page":"3898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8738999962806702,"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":0.8738999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02199999988079071,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.021800000220537186,"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":0.6292999982833862},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6208000183105469},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.538100004196167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4810999929904938},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4108999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560999989509583},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6292999982833862},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5927000045776367},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.538100004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36980000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3746252.3761051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416078647.pdf","grobid_xml":"https://content.openalex.org/works/W4416078647.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2108218871","https://openalex.org/W2222512263","https://openalex.org/W2296283641","https://openalex.org/W2760146825","https://openalex.org/W2803609931","https://openalex.org/W2950281195","https://openalex.org/W2952594430","https://openalex.org/W2963341956","https://openalex.org/W2963568202","https://openalex.org/W3034744126","https://openalex.org/W3034999214","https://openalex.org/W3035375600","https://openalex.org/W3035625205","https://openalex.org/W3096609285","https://openalex.org/W3104990845","https://openalex.org/W3155429205","https://openalex.org/W3171116005","https://openalex.org/W3172087149","https://openalex.org/W3175225269","https://openalex.org/W3176680950","https://openalex.org/W3187731984","https://openalex.org/W3207397751","https://openalex.org/W4225794827","https://openalex.org/W4226436348","https://openalex.org/W4285295138","https://openalex.org/W4382202726","https://openalex.org/W4385567543","https://openalex.org/W4385571159","https://openalex.org/W4385571881","https://openalex.org/W4386001503","https://openalex.org/W4386075800","https://openalex.org/W4387846420","https://openalex.org/W4390873541","https://openalex.org/W4390873752","https://openalex.org/W4391840390","https://openalex.org/W4392931179","https://openalex.org/W4394717739","https://openalex.org/W4394733949","https://openalex.org/W4396816741","https://openalex.org/W4401042320","https://openalex.org/W4401525457","https://openalex.org/W4402671644","https://openalex.org/W4411120260","https://openalex.org/W6927916266"],"related_works":[],"abstract_inverted_index":{"Named":[0],"entity":[1,25,63,83,98,110,167],"recognition":[2],"(NER)":[3],"is":[4],"a":[5,36,55,88,91,180],"key":[6],"task":[7,53],"in":[8],"natural":[9],"language":[10],"processing,":[11],"but":[12],"existing":[13,218],"methods":[14],"often":[15],"fail":[16],"to":[17,23,80,96,153],"effectively":[18,135],"handle":[19],"nested":[20,38,51,191],"structures":[21],"due":[22],"fuzzy":[24],"boundaries":[26],"and":[27,109,124,134,148,175,197,207],"structural":[28],"ambiguity.":[29],"To":[30,102],"address":[31],"this":[32],"challenge,":[33],"we":[34,112],"propose":[35],"novel":[37],"NER":[39,52,192,204],"method":[40,215],"based":[41],"on":[42,189],"an":[43,114],"IoU-aware":[44,115],"denoising":[45,57,159],"diffusion":[46,183],"model,":[47],"which":[48],"formulates":[49],"the":[50,81,104,120,158,163,213],"as":[54,150,199,201],"generative":[56],"process":[58],"that":[59,118,212],"progressively":[60],"recovers":[61],"gold":[62],"spans":[64,174],"from":[65,171],"noisy":[66,71],"span":[67,99],"proposals.":[68],"We":[69,85,185],"generate":[70],"samples":[72],"during":[73],"training":[74],"by":[75,139,169],"gradually":[76],"adding":[77],"Gaussian":[78],"noise":[79,173],"ground-truth":[82,125],"boundaries.":[84],"then":[86],"train":[87],"denoiser":[89],"incorporating":[90],"top-k":[92],"selective":[93],"attention":[94],"mechanism":[95],"refine":[97],"proposals":[100],"iteratively.":[101],"strengthen":[103],"alignment":[105],"between":[106,122],"boundary":[107,132],"localization":[108],"classification,":[111],"introduce":[113],"loss":[116],"function":[117],"optimizes":[119],"overlap":[121],"predicted":[123],"spans.":[126],"This":[127],"design":[128],"more":[129],"accurately":[130],"guides":[131],"regression":[133,141],"reduces":[136],"misalignment":[137],"caused":[138],"conventional":[140],"losses.":[142],"Our":[143],"model":[144,164],"leverages":[145],"sentence":[146],"features":[147],"timesteps":[149],"conditional":[151],"inputs":[152],"capture":[154],"contextual":[155],"information":[156],"throughout":[157],"process.":[160,184],"During":[161],"inference,":[162],"generates":[165],"final":[166],"predictions":[168],"starting":[170],"random":[172],"iteratively":[176],"refining":[177],"them":[178],"through":[179],"multi-step":[181],"reverse":[182],"conduct":[186],"extensive":[187],"experiments":[188],"four":[190],"datasets,":[193,205],"ACE2004,":[194],"ACE2005,":[195],"GENIA,":[196],"KBP2017,":[198],"well":[200],"two":[202],"flat":[203],"CoNLL2003":[206],"OntoNotes.":[208],"Experimental":[209],"results":[210],"show":[211],"proposed":[214],"consistently":[216],"outperforms":[217],"advanced":[219],"models":[220],"across":[221],"all":[222],"benchmarks,":[223],"demonstrating":[224],"its":[225],"effectiveness.":[226]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-10T00:00:00"}