{"id":"https://openalex.org/W7166890263","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1105","title":"INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents","display_name":"INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166890263","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1105"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1105","pdf_url":"https://aclanthology.org/2026.findings-acl.1105.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.1105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133678543","display_name":"Somraj Gautam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Somraj Gautam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115042477","display_name":"Anathapindika Dravichi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anathapindika Dravichi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025684791","display_name":"Gaurav Harit","orcid":"https://orcid.org/0000-0001-7943-0123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaurav Harit","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":0.87833812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21969","last_page":"21981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23510000109672546,"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":0.23510000109672546,"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":0.2084999978542328,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10830000042915344,"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/table","display_name":"Table (database)","score":0.5625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49129998683929443},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27559998631477356},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2630999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766999959945679},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24050000309944153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1105","pdf_url":"https://aclanthology.org/2026.findings-acl.1105.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.1105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1105","pdf_url":"https://aclanthology.org/2026.findings-acl.1105.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":[{"score":0.7860424518585205,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166890263.pdf","grobid_xml":"https://content.openalex.org/works/W7166890263.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"INDOTABVQA,":[2],"a":[3,99,104,163],"benchmark":[4,77],"for":[5,136,166],"evaluating":[6],"cross-lingual":[7,68],"Table":[8],"Visual":[9],"Question":[10],"Answering":[11],"(VQA)":[12],"on":[13,91,108,157],"real-world":[14],"document":[15,23,159,172],"images":[16,24],"in":[17,44,59,74,96,116,169,175],"Bahasa":[18,47,65],"Indonesia.The":[19],"dataset":[20,110,181],"comprises":[21],"1,593":[22,41],"across":[25],"three":[26],"visual":[27],"styles":[28],"(bordered,":[29],"borderless,":[30],"and":[31,40,51,67,83,85,95,103,113,147],"colorful)":[32],"with":[33,64,72],"one":[34,38],"or":[35],"more":[36],"than":[37],"tables,":[39],"question-answer":[42],"sets":[43],"four":[45],"languages:":[46],"Indonesia,":[48],"English,":[49],"Hindi,":[50],"Arabic.This":[52],"enables":[53],"evaluation":[54],"of":[55,133,143,178],"Vision-Language":[56],"Models":[57],"(VLMs)":[58],"both":[60],"monolingual":[61],"(Bahasa":[62,70],"documents":[63,71],"questions)":[66],"settings":[69],"questions":[73],"other":[75],"languages).We":[76],"leading":[78],"open-source":[79],"VLMs":[80],"(Qwen2.5-VL,Gemma-3,":[81],"LLaMA-3.2)":[82],"GPT-4o":[84],"reveal":[86],"substantial":[87],"performance":[88,127,156],"gaps,":[89],"particularly":[90],"structurally":[92],"complex":[93],"tables":[94],"lowresource":[97],"languages.Fine-tuning":[98],"compact":[100],"3B":[101],"model":[102,107],"LoRA-finetuned":[105],"7B":[106],"our":[109],"yields":[111],"11.6%":[112],"17.8%":[114],"improvements":[115],"accuracy.Providing":[117],"explicit":[118],"table":[119],"region":[120],"coordinates":[121],"as":[122],"additional":[123],"input":[124],"further":[125],"improves":[126],"by":[128],"4-7%,":[129],"demonstrating":[130],"the":[131,141,179],"value":[132],"Spatial":[134],"priors":[135],"table-based":[137],"reasoning.Our":[138],"findings":[139],"underscore":[140],"importance":[142],"language-diverse,":[144],"domain-specific":[145],"datasets":[146],"demonstrate":[148],"that":[149],"targeted":[150],"finetuning":[151],"can":[152],"significantly":[153],"enhance":[154],"VLM":[155],"specialized":[158],"understanding":[160],"tasks.INDOTABVQA":[161],"provides":[162],"valuable":[164],"resource":[165],"advancing":[167],"research":[168],"crosslingual,":[170],"structure-aware":[171],"understanding,":[173],"especially":[174],"underrepresented":[176],"regions":[177],"world.The":[180],"is":[182],"publicly":[183],"available":[184],"via":[185],"Hugging":[186],"Face":[187],"at:":[188],"https://huggingface.co/":[189],"datasets/NusaBharat/INDOTABVQA.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}