{"id":"https://openalex.org/W4416035988","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.51","title":"DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms","display_name":"DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035988","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.51"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.51","pdf_url":"https://aclanthology.org/2025.findings-emnlp.51.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.51.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016901770","display_name":"Xiaojun Bi","orcid":"https://orcid.org/0000-0002-9716-7709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun Bi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025707866","display_name":"Shuo Li","orcid":"https://orcid.org/0000-0002-3488-6028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036782157","display_name":"Junyao Xing","orcid":"https://orcid.org/0000-0003-2773-9588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyao Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029991239","display_name":"Ziyue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyue Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114124897","display_name":"Fuwen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuwen Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040899184","display_name":"Weizheng Qiao","orcid":"https://orcid.org/0000-0002-6770-4497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizheng Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004960501","display_name":"Lu Han","orcid":"https://orcid.org/0000-0001-7198-3380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ziwei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101953295","display_name":"Peng Li","orcid":"https://orcid.org/0009-0008-0942-6565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3758,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93447166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2410999983549118,"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":0.2410999983549118,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0763000026345253,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.06120000034570694,"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/pictogram","display_name":"Pictogram","score":0.6735000014305115},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4699999988079071},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.2978000044822693},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.27469998598098755},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27309998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C7220189","wikidata":"https://www.wikidata.org/wiki/Q52827","display_name":"Pictogram","level":2,"score":0.6735000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.51","pdf_url":"https://aclanthology.org/2025.findings-emnlp.51.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.51","pdf_url":"https://aclanthology.org/2025.findings-emnlp.51.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1681167796","display_name":null,"funder_award_id":"62236011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2336663847","display_name":null,"funder_award_id":"ZD279","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund 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/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035988.pdf","grobid_xml":"https://content.openalex.org/works/W4416035988.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dongba":[0,34,53,60,107],"pictographic":[1,5],"is":[2,126],"the":[3,11,24,98,119],"only":[4],"script":[6],"still":[7,127],"in":[8,10,68],"use":[9],"world.Its":[12],"pictorial":[13],"ideographic":[14],"features":[15],"carry":[16],"rich":[17],"cultural":[18],"and":[19,63,73,87,112],"contextual":[20],"information.However,":[21],"due":[22],"to":[23,102],"lack":[25],"of":[26,33,52,57,59,90,106,123],"relevant":[27],"datasets,":[28],"research":[29],"on":[30,48],"semantic":[31,66,82],"understanding":[32],"hieroglyphs":[35,108],"has":[36],"progressed":[37],"slowly.To":[38],"this":[39],"end,":[40],"we":[41],"constructed":[42],"DongbaMIE":[43],"-the":[44],"first":[45],"dataset":[46,55],"focusing":[47],"multimodal":[49,92],"information":[50,104],"extraction":[51,105,122],"pictograms.The":[54],"consists":[56],"images":[58],"hieroglyphic":[61],"characters":[62],"their":[64],"corresponding":[65],"annotations":[67,79],"Chinese.It":[69],"contains":[70],"23,530":[71],"sentence-level":[72],"2,539":[74],"paragraph-level":[75],"high-quality":[76],"text-image":[77],"pairs.The":[78],"cover":[80],"four":[81],"dimensions:":[83],"object,":[84],"action,":[85],"relation":[86],"attribute.Systematic":[88],"evaluation":[89],"mainstream":[91],"large":[93],"language":[94],"models":[95,99],"shows":[96],"that":[97],"are":[100],"difficult":[101],"perform":[103],"efficiently":[109],"under":[110],"zeroshot":[111],"few-shot":[113],"learning.Although":[114],"supervised":[115],"fine-tuning":[116],"can":[117],"improve":[118],"performance,":[120],"accurate":[121],"complex":[124],"semantics":[125],"a":[128],"great":[129],"challenge":[130],"at":[131],"present.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-11-08T00:00:00"}