{"id":"https://openalex.org/W7155499912","doi":"https://doi.org/10.1162/tacl.a.633","title":"MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking","display_name":"MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7155499912","doi":"https://doi.org/10.1162/tacl.a.633"},"language":"en","primary_location":{"id":"doi:10.1162/tacl.a.633","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.633","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.633/2597128/tacl.a.633.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.633/2597128/tacl.a.633.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036353926","display_name":"Sathyanarayanan Ramamoorthy","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sathyanarayanan Ramamoorthy","raw_affiliation_strings":["Carnegie Mellon University, USA. sramamoo@cs.cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA. sramamoo@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134488960","display_name":"Vishwa Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishwa Shah","raw_affiliation_strings":["Carnegie Mellon University, USA. vishwavs@cs.cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA. vishwavs@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052885801","display_name":"Simran Khanuja","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130200","display_name":"Carnegie Mellon University Africa","ror":"https://ror.org/02f33m021","country_code":"RW","type":"education","lineage":["https://openalex.org/I4210130200","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["RW","US"],"is_corresponding":false,"raw_author_name":"Simran Khanuja","raw_affiliation_strings":["Carnegie Mellon University, USA. skhanuja@cs.cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA. skhanuja@cs.cmu.edu","institution_ids":["https://openalex.org/I4210130200","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134518746","display_name":"Zaid Sheikh","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Sheikh","raw_affiliation_strings":["Carnegie Mellon University, USA. zsheikh@cs.cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA. zsheikh@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134514949","display_name":"Shan Jie","orcid":null},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shan Jie","raw_affiliation_strings":["Defence Science and Technology Agency, Singapore. yshanjie@dsta.gov.sg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defence Science and Technology Agency, Singapore. yshanjie@dsta.gov.sg","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005248930","display_name":"Ann Chia","orcid":null},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ann Chia","raw_affiliation_strings":["Defence Science and Technology Agency, Singapore. achiajin@dsta.gov.sg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defence Science and Technology Agency, Singapore. achiajin@dsta.gov.sg","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134493069","display_name":"Shearman Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I2802950585","display_name":"Defence Science and Technology Agency","ror":"https://ror.org/02rvm6b03","country_code":"SG","type":"government","lineage":["https://openalex.org/I1325159990","https://openalex.org/I2802950585"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shearman Chua","raw_affiliation_strings":["Defence Science and Technology Agency, Singapore. schuawei@dsta.gov.sg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defence Science and Technology Agency, Singapore. schuawei@dsta.gov.sg","institution_ids":["https://openalex.org/I2802950585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134505315","display_name":"Graham Neubig","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University, USA. gneubig@cs.cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA. gneubig@cs.cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.40596344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"399","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7918000221252441,"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":0.7918000221252441,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03669999912381172,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.03200000151991844,"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/entity-linking","display_name":"Entity linking","score":0.8086000084877014},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7597000002861023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7124999761581421},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6599000096321106},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5697000026702881},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3718999922275543},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3294999897480011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9240999817848206},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.8086000084877014},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7597000002861023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6312000155448914},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5697000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25200000405311584},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl.a.633","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.633","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.633/2597128/tacl.a.633.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1162/tacl.a.633","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl.a.633","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/TACL.a.633/2597128/tacl.a.633.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7174055576324463,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334743","display_name":"Defence Science and Technology Agency - Singapore","ror":"https://ror.org/02rvm6b03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155499912.pdf","grobid_xml":"https://content.openalex.org/works/W7155499912.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1988157164","https://openalex.org/W2798832674","https://openalex.org/W2952826391","https://openalex.org/W2963662654","https://openalex.org/W2963722184","https://openalex.org/W3014809049","https://openalex.org/W3016001968","https://openalex.org/W3035032094","https://openalex.org/W3100843744","https://openalex.org/W3102844651","https://openalex.org/W3104748221","https://openalex.org/W3136215575","https://openalex.org/W3141830881","https://openalex.org/W3205420591","https://openalex.org/W3206010442","https://openalex.org/W4224134764","https://openalex.org/W4285157771","https://openalex.org/W4285286514","https://openalex.org/W4294214983","https://openalex.org/W4297029908","https://openalex.org/W4322706667","https://openalex.org/W4386576724","https://openalex.org/W4387969337","https://openalex.org/W4396773040","https://openalex.org/W4411630009","https://openalex.org/W7131792124"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"introduces":[3],"MERLIN,":[4],"a":[5],"novel":[6],"testbed":[7],"system":[8],"for":[9,84,96],"the":[10,78,87,106,108],"task":[11],"of":[12,80],"Multilingual":[13],"Multimodal":[14],"Entity":[15],"Linking.":[16],"The":[17],"created":[18],"dataset":[19],"includes":[20],"BBC":[21],"news":[22],"article":[23],"titles,":[24],"paired":[25],"with":[26],"corresponding":[27],"images,":[28],"in":[29],"five":[30],"languages:":[31],"Hindi,":[32],"Japanese,":[33],"Indonesian,":[34],"Vietnamese,":[35],"and":[36,57,68,94],"Tamil,":[37],"featuring":[38],"over":[39],"7,000":[40],"named":[41],"entity":[42,59,81],"mentions":[43],"linked":[44],"to":[45],"2,500":[46],"unique":[47],"Wikidata":[48],"entities.":[49],"We":[50],"also":[51],"include":[52],"several":[53],"benchmarks":[54],"using":[55],"multilingual":[56,103],"multimodal":[58],"linking":[60],"methods":[61,110],"exploring":[62],"different":[63],"language":[64],"models":[65,97],"like":[66],"LLaMa-2":[67],"Aya-23.":[69],"Our":[70],"findings":[71],"indicate":[72],"that":[73,98],"incorporating":[74],"visual":[75],"data":[76],"improves":[77],"accuracy":[79],"linking,":[82],"especially":[83],"entities":[85],"where":[86],"textual":[88],"context":[89],"is":[90],"ambiguous":[91],"or":[92],"insufficient,":[93],"particularly":[95],"do":[99],"not":[100],"have":[101],"strong":[102],"abilities.":[104],"For":[105],"work,":[107],"dataset,":[109],"are":[111],"available":[112],"online.1":[113]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-04-25T00:00:00"}
