{"id":"https://openalex.org/W7166849833","doi":"https://doi.org/10.18653/v1/2026.acl-long.1356","title":"Zero-shot Jianzi Recognition as Structured Visual Information Extraction in Open Compositional Symbolic Systems","display_name":"Zero-shot Jianzi Recognition as Structured Visual Information Extraction in Open Compositional Symbolic Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166849833","doi":"https://doi.org/10.18653/v1/2026.acl-long.1356"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1356","pdf_url":"https://aclanthology.org/2026.acl-long.1356.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1356.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139716550","display_name":"Zehan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehan Li","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773100","display_name":"Fu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745914","display_name":"Zhijun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Liu","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102477484","display_name":"Jingwei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Cheng","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87259644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29414","last_page":"29429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.125900000333786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.125900000333786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.1103999987244606,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.033399999141693115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4083999991416931},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36980000138282776},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.3361999988555908},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.31060001254081726},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.30320000648498535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2985999882221222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6484000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1356","pdf_url":"https://aclanthology.org/2026.acl-long.1356.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1356","pdf_url":"https://aclanthology.org/2026.acl-long.1356.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2799773603","display_name":null,"funder_award_id":"62276057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166849833.pdf","grobid_xml":"https://content.openalex.org/works/W7166849833.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Guqin":[0,155],"(\u53e4":[1],"\u7434)":[2],"Jianzi":[3,48,52,132,145,156],"(\u6e1b":[4],"\u5b57)":[5],"is":[6],"an":[7],"open":[8],"and":[9,33,37,43,85,89,147],"freely":[10],"compositional":[11],"tablature":[12],"system":[13],"that":[14,119],"encodes":[15],"performance":[16],"actions":[17],"rather":[18],"than":[19],"acoustic":[20],"outcomes.Its":[21],"automatic":[22],"recognition":[23,53,146],"remains":[24],"largely":[25],"unexplored,":[26],"as":[27,54],"conventional":[28],"OCR":[29],"assumes":[30],"a":[31,62,91,100],"closed":[32],"enumerable":[34],"glyph":[35],"set":[36],"struggles":[38],"with":[39],"Jianzi's":[40],"unbounded":[41],"composition":[42,74],"manuscript-level":[44],"variability.We":[45],"introduce":[46],"Zero-shot":[47],"Recognition,":[49],"which":[50],"formulates":[51],"visionto-sequence":[55],"prediction":[56],"of":[57,142,153],"canonical":[58],"component":[59,95],"sequences":[60],"under":[61],"zero-shot":[63],"split.To":[64],"enable":[65],"scalable":[66],"supervision,":[67],"we":[68],"construct":[69],"Synthetic-JZ":[70],"from":[71],"aligned":[72],"online":[73],"metadata.We":[75],"then":[76],"synthesize":[77],"manuscriptlike":[78],"training":[79],"images":[80],"via":[81],"component-wise":[82],"style":[83],"recomposition":[84],"manuscript-domain":[86],"noise":[87],"modeling,":[88],"fine-tune":[90],"VLM":[92],"for":[93,150],"end-toend":[94],"sequence":[96,124],"recognition.At":[97],"inference":[98],"time,":[99],"lightweight":[101],"legality-guided":[102],"correction":[103],"module":[104],"re-ranks":[105],"decoding":[106],"candidates,":[107],"suppressing":[108],"structural":[109],"hallucinations":[110],"without":[111],"modifying":[112],"the":[113,140],"backbone.Experiments":[114],"on":[115,126],"two":[116],"benchmarks":[117],"show":[118],"our":[120,128],"method":[121],"achieves":[122],"63.02%":[123],"accuracy":[125],"Real-JZ,":[127],"manually":[129],"annotated":[130],"realworld":[131],"benchmark,":[133],"surpassing":[134],"Gemini-3-Pro":[135],"by":[136],"35.11%.This":[137],"result":[138],"highlights":[139],"feasibility":[141],"reliable":[143],"automated":[144],"its":[148],"potential":[149],"large-scale":[151],"digitization":[152],"historical":[154],"Pu":[157],"manuscripts.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}