{"id":"https://openalex.org/W4412888480","doi":"https://doi.org/10.18653/v1/2025.findings-acl.268","title":"NovelCR: A Large-Scale Bilingual Dataset Tailored for Long-Span Coreference Resolution","display_name":"NovelCR: A Large-Scale Bilingual Dataset Tailored for Long-Span Coreference Resolution","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888480","doi":"https://doi.org/10.18653/v1/2025.findings-acl.268"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.268","pdf_url":"https://aclanthology.org/2025.findings-acl.268.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.268.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055939662","display_name":"Meihan Tong","orcid":"https://orcid.org/0000-0003-2679-5641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MeiHan Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328371","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-5073-3371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Wang","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":0.14379741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5161","last_page":"5173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9050999879837036,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9050999879837036,"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/coreference","display_name":"Coreference","score":0.928697943687439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713088870048523},{"id":"https://openalex.org/keywords/span","display_name":"Span (engineering)","score":0.649564266204834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5964994430541992},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5876792073249817},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5833062529563904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245266556739807},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11244133114814758},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0689949095249176},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06738254427909851}],"concepts":[{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.928697943687439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713088870048523},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.649564266204834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5964994430541992},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5876792073249817},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5833062529563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245266556739807},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11244133114814758},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0689949095249176},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06738254427909851},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.268","pdf_url":"https://aclanthology.org/2025.findings-acl.268.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.268","pdf_url":"https://aclanthology.org/2025.findings-acl.268.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888480.pdf","grobid_xml":"https://content.openalex.org/works/W4412888480.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3041549465","https://openalex.org/W2380610138","https://openalex.org/W3171444480","https://openalex.org/W4206648670","https://openalex.org/W1495336436","https://openalex.org/W3212412177","https://openalex.org/W3173436410","https://openalex.org/W2925144130","https://openalex.org/W1594011529","https://openalex.org/W2339319059"],"abstract_inverted_index":{"Coreference":[0],"resolution":[1,32],"(CR)":[2],"links":[3],"pronouns":[4],"and":[5,60,80,99],"noun":[6],"phrases":[7],"to":[8,33],"their":[9],"referent":[10],"entities,":[11],"serving":[12],"as":[13],"a":[14,34,43,93],"key":[15],"step":[16],"in":[17,27,58,63,70,78,82],"deep":[18],"text":[19,36],"understanding.Presently":[20],"available":[21,113],"CR":[22],"datasets":[23],"are":[24],"either":[25],"small":[26],"scale":[28],"or":[29,87],"restrict":[30],"coreference":[31,50,72],"limited":[35],"span.In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"NovelCR,":[42],"large-scale":[44],"bilingual":[45],"benchmark":[46],"designed":[47],"for":[48],"long-span":[49,71],"resolution.NovelCR":[51],"features":[52],"extensive":[53],"annotations,":[54],"including":[55],"148k":[56],"mentions":[57,62],"NovelCR-en":[59,79],"311k":[61],"NovelCR-zh.Moreover,":[64],"the":[65],"dataset":[66,110],"is":[67,111],"notably":[68],"rich":[69],"pairs,":[73],"with":[74],"85%":[75],"of":[76],"pairs":[77],"83%":[81],"NovelCR-zh":[83],"spanning":[84],"across":[85],"three":[86],"more":[88],"sentences.Experiments":[89],"on":[90],"NovelCR":[91,104,109],"reveal":[92],"large":[94],"gap":[95],"between":[96],"state-of-the-art":[97],"baselines":[98],"human":[100],"performance,":[101],"highlighting":[102],"that":[103],"remains":[105],"an":[106],"open":[107],"issue.The":[108],"publicly":[112],"at:":[114]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}