{"id":"https://openalex.org/W4408345722","doi":"https://doi.org/10.1109/icassp49660.2025.10889935","title":"DiffMEL: A large-scale difficulty-graded dataset for Multimodal Entity Linking","display_name":"DiffMEL: A large-scale difficulty-graded dataset for Multimodal Entity Linking","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345722","doi":"https://doi.org/10.1109/icassp49660.2025.10889935"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100744800","display_name":"Fang Wang","orcid":"https://orcid.org/0000-0003-3567-9108"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Wang","raw_affiliation_strings":["Peking University,School of Computer Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062486535","display_name":"Xiaoying Bai","orcid":"https://orcid.org/0000-0003-3989-4075"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoying Bai","raw_affiliation_strings":["Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069783147","display_name":"Tianwei Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianwei Yan","raw_affiliation_strings":["National University of Defense Technology,College of Computer,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030248582","display_name":"Minghao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Hu","raw_affiliation_strings":["Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Institute of Big Data, Beijing, (AIBD),Beijing,China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081654212","display_name":"Yi Liang","orcid":"https://orcid.org/0000-0001-6481-0692"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.9897000193595886,"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":0.9624999761581421,"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":0.9390000104904175,"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":0.718680739402771},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6250600218772888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4313998520374298},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38305652141571045},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3288535177707672},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07337146997451782},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06835466623306274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718680739402771},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6250600218772888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4313998520374298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38305652141571045},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3288535177707672},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07337146997451782},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06835466623306274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W173870552","https://openalex.org/W2134150392","https://openalex.org/W2185175083","https://openalex.org/W2561391765","https://openalex.org/W2788647998","https://openalex.org/W2798298921","https://openalex.org/W2798832674","https://openalex.org/W2898256678","https://openalex.org/W2904565150","https://openalex.org/W2947312908","https://openalex.org/W2963518342","https://openalex.org/W2970364616","https://openalex.org/W2982573303","https://openalex.org/W3016211260","https://openalex.org/W3032553678","https://openalex.org/W3034689697","https://openalex.org/W3106859150","https://openalex.org/W3141830881","https://openalex.org/W3205420591","https://openalex.org/W3211405508","https://openalex.org/W3216854409","https://openalex.org/W4224134764","https://openalex.org/W4365142059","https://openalex.org/W4385567248","https://openalex.org/W4402753874","https://openalex.org/W6639432524","https://openalex.org/W6775188310","https://openalex.org/W6778377612","https://openalex.org/W6791353385","https://openalex.org/W6851592950","https://openalex.org/W6855350031","https://openalex.org/W6857055646","https://openalex.org/W6858268588","https://openalex.org/W6873487245","https://openalex.org/W6876048176"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0,10],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"tremendous":[7],"potential":[8],"in":[9,24,33,147],"Entity":[11],"Linking":[12],"(MEL).":[13],"However,":[14],"they":[15],"are":[16],"still":[17],"far":[18],"from":[19],"achieving":[20],"the":[21,34,51,71,74,78,86,100],"expected":[22],"effectiveness":[23],"practical":[25],"applications.":[26],"This":[27],"could":[28],"be":[29],"due":[30],"to":[31,133],"limitations":[32],"MEL":[35,41,91,106,148],"dataset":[36,104,154],"used":[37],"for":[38,105],"training.":[39],"Existing":[40],"datasets":[42],"primarily":[43],"focus":[44],"on":[45,90],"simple":[46],"tasks":[47,124],"and":[48,81,113,125],"only":[49],"consider":[50],"direct":[52],"matching":[53],"of":[54,65,73,88,107],"mentions":[55,64],"with":[56,144],"labeled":[57],"entities":[58],"within":[59,77],"a":[60,150],"multimodal":[61],"context,":[62],"ignoring":[63],"unmatched":[66],"entities.":[67],"Factors":[68],"such":[69],"as":[70],"presence":[72],"ground-truth":[75],"entity":[76,128],"candidate":[79],"set":[80],"its":[82],"position":[83],"directly":[84],"impact":[85],"performance":[87],"MLLMs":[89,143],"tasks.":[92],"To":[93],"tackle":[94],"these":[95],"obstacles,":[96],"we":[97],"constructed":[98],"DiffMEL,":[99],"first":[101],"large-scale":[102],"difficulty-graded":[103],"MLLMs.":[108,137],"DiffMEL":[109,132,141],"contains":[110],"79,625":[111],"instances":[112],"318.5K":[114],"instance-related":[115],"high-resolution":[116],"images,":[117],"covering":[118],"3":[119],"various":[120],"difficulty":[121],"graded":[122],"linking":[123],"5":[126],"different":[127],"themes.":[129],"We":[130],"utilize":[131],"train":[134],"several":[135],"open-source":[136],"Experiment":[138],"results":[139],"demonstrate":[140],"empowers":[142],"stronger":[145],"capabilities":[146],"by":[149],"large-margin":[151],"(5%-56.1%).":[152],"our":[153],"is":[155],"now":[156],"available":[157],"at":[158],"https://github.com/ww-ffff/DiffMEL.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}