{"id":"https://openalex.org/W4415536699","doi":"https://doi.org/10.1145/3746027.3755444","title":"Multi-Modal Semantic Parsing for the Interpretation of Tombstone Inscriptions","display_name":"Multi-Modal Semantic Parsing for the Interpretation of Tombstone Inscriptions","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536699","doi":"https://doi.org/10.1145/3746027.3755444"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755444","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100320912","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-9582-7662"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9582-7662","affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002288369","display_name":"Johan Bos","orcid":"https://orcid.org/0000-0002-9079-5438"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johan Bos","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9079-5438","affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32391421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6672","last_page":"6681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9958999752998352,"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":0.9955000281333923,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9714000225067139,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6830999851226807},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.6597999930381775},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6304000020027161},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5900999903678894},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6304000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6043000221252441},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5753999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C164767435","wikidata":"https://www.wikidata.org/wiki/Q28823","display_name":"Textile","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3755444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755444","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire/ed441661-90af-47b4-83b7-443b9cf7ca8d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/ed441661-90af-47b4-83b7-443b9cf7ca8d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhang, X & Bos, J 2025, Multi-Modal Semantic Parsing for the Interpretation of Tombstone Inscriptions. in MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025. MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025, Association for Computing Machinery, Inc, pp. 6672-6681, 33rd ACM International Conference on Multimedia, MM 2025, Dublin, Ireland, 27/10/2025. https://doi.org/10.1145/3746027.3755444","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:publications/ed441661-90af-47b4-83b7-443b9cf7ca8d","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/ed441661-90af-47b4-83b7-443b9cf7ca8d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhang, X & Bos, J 2025, Multi-Modal Semantic Parsing for the Interpretation of Tombstone Inscriptions. in MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025. MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025, Association for Computing Machinery, Inc, pp. 6672-6681, 33rd ACM International Conference on Multimedia, MM 2025, Dublin, Ireland, 27/10/2025. https://doi.org/10.1145/3746027.3755444","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755444","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1987586324","https://openalex.org/W2023996190","https://openalex.org/W2065253778","https://openalex.org/W2131429178","https://openalex.org/W2475275044","https://openalex.org/W2509704507","https://openalex.org/W2528248059","https://openalex.org/W2898774411","https://openalex.org/W2962906084","https://openalex.org/W3008329436","https://openalex.org/W3037095066","https://openalex.org/W3103699753","https://openalex.org/W3208068144","https://openalex.org/W4220941542","https://openalex.org/W4235505822","https://openalex.org/W4285059449","https://openalex.org/W4386535062","https://openalex.org/W4389518944","https://openalex.org/W4403120224","https://openalex.org/W4404781984","https://openalex.org/W4405428501"],"related_works":[],"abstract_inverted_index":{"Tombstones":[0],"are":[1,171],"historically":[2],"and":[3,14,31,52,76,99,129,132,168],"culturally":[4],"rich":[5],"artifacts,":[6],"encapsulating":[7],"individual":[8],"lives,":[9],"community":[10],"memory,":[11],"historical":[12],"narratives":[13],"artistic":[15],"expression.":[16],"Yet,":[17],"many":[18],"tombstones":[19],"today":[20],"face":[21],"significant":[22],"preservation":[23],"challenges,":[24],"including":[25],"physical":[26,134],"erosion,":[27],"vandalism,":[28],"environmental":[29],"degradation,":[30],"political":[32],"shifts.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,84,121],"introduce":[38],"a":[39],"novel":[40],"multi-modal":[41],"framework":[42],"for":[43,163],"tombstone":[44,55,65,155],"digitization,":[45],"aiming":[46],"to":[47,63,89,103,118,139,153],"improve":[48],"the":[49,123,150],"interpretation,":[50],"organization":[51],"retrieval":[53],"of":[54,116],"content.":[56],"Our":[57,147],"approach":[58],"leverages":[59],"vision-language":[60,159],"models":[61],"(VLMs)":[62],"translate":[64],"images":[66],"into":[67],"structured":[68],"Tombstone":[69],"Meaning":[70],"Representations":[71],"(TMRs),":[72],"capturing":[73],"both":[74],"image":[75,137],"text":[77],"information.":[78],"To":[79],"further":[80],"enrich":[81],"semantic":[82],"parsing,":[83],"incorporate":[85],"retrieval-augmented":[86],"generation":[87],"(RAG)":[88],"integrate":[90],"externally":[91],"dependent":[92],"elements":[93],"such":[94],"as":[95],"toponyms,":[96],"occupation":[97],"codes,":[98],"ontological":[100],"concepts.":[101],"Compared":[102],"traditional":[104],"OCR-based":[105],"pipelines,":[106],"our":[107],"method":[108],"improves":[109],"parsing":[110],"accuracy":[111],"from":[112],"an":[113],"F1":[114],"score":[115],"36.1":[117],"89.5.":[119],"Furthermore,":[120],"evaluate":[122],"model's":[124],"robustness":[125],"across":[126],"diverse":[127],"linguistic":[128],"cultural":[130],"inscriptions,":[131],"simulate":[133],"degradation":[135],"through":[136],"fusion":[138],"assess":[140],"performance":[141],"under":[142],"noisy":[143],"or":[144],"damaged":[145],"conditions.":[146],"work":[148],"represents":[149],"first":[151],"attempt":[152],"formalize":[154],"understanding":[156],"using":[157],"large":[158],"models,":[160],"presenting":[161],"implications":[162],"heritage":[164],"preservation.":[165],"The":[166],"code":[167],"supplementary":[169],"materials":[170],"available":[172],"at:":[173],"https://github.com/LastDance500/Tombstone-Parsing.":[174]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-25T00:00:00"}
