{"id":"https://openalex.org/W4412887981","doi":"https://doi.org/10.18653/v1/2025.findings-acl.762","title":"ChuLo: Chunk-Level Key Information Representation for Long Document Understanding","display_name":"ChuLo: Chunk-Level Key Information Representation for Long Document Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887981","doi":"https://doi.org/10.18653/v1/2025.findings-acl.762"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.762","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.762","pdf_url":"https://aclanthology.org/2025.findings-acl.762.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.762.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100664684","display_name":"Danni Li","orcid":"https://orcid.org/0000-0002-0608-2831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Caren Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caren Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113939949","display_name":"Yue Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010425049","display_name":"Feiqi Cao","orcid":"https://orcid.org/0000-0002-4910-5925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiqi Cao","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":5.755,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95797674,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14756","last_page":"14773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9848999977111816,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9848999977111816,"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/T10028","display_name":"Topic Modeling","score":0.9402999877929688,"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/computer-science","display_name":"Computer science","score":0.7730951309204102},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.771665096282959},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6158166527748108},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5743901133537292},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08026435971260071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730951309204102},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.771665096282959},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6158166527748108},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5743901133537292},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08026435971260071},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.762","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.762","pdf_url":"https://aclanthology.org/2025.findings-acl.762.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"},{"id":"pmh:oai:pure.atira.dk:openaire/fc2a20ce-2fc2-4632-bd94-e5b1a8db3e3d","is_oa":true,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/fc2a20ce-2fc2-4632-bd94-e5b1a8db3e3d","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Y, Han, S C, Dai, Y & Cao, F 2025, ChuLo : Chunk-Level Key Information Representation for Long Document Understanding. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), Findings of the Association for Computational Linguistics : ACL 2025. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 14756-14773, 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria, 27/07/25. https://doi.org/10.18653/v1/2025.findings-acl.762","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.762","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.762","pdf_url":"https://aclanthology.org/2025.findings-acl.762.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887981.pdf","grobid_xml":"https://content.openalex.org/works/W4412887981.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Transformer-based":[0,105],"models":[1],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,109],"various":[7],"Natural":[8],"Language":[9],"Processing":[10],"(NLP)":[11],"tasks,":[12,116,148],"yet":[13],"their":[14],"ability":[15,50],"to":[16,35,43,51,87,119],"handle":[17],"long":[18,66,110,139,144],"documents":[19],"is":[20,117,159],"constrained":[21],"by":[22],"computational":[23],"limitations.Traditional":[24],"approaches,":[25],"such":[26],"as":[27],"truncating":[28],"inputs,":[29],"sparse":[30],"self-attention,":[31],"and":[32,46,100,143,155],"chunking,":[33],"attempt":[34],"mitigate":[36],"these":[37,71],"issues,":[38],"but":[39],"they":[40],"often":[41],"lead":[42],"information":[44,98],"loss":[45,99],"hinder":[47],"the":[48,102,127],"model's":[49],"capture":[52],"long-range":[53],"dependencies.In":[54],"this":[55],"paper,":[56],"we":[57],"introduce":[58],"ChuLo,":[59],"a":[60],"novel":[61],"chunk":[62],"representation":[63],"method":[64,136],"for":[65],"document":[67,90,111,140,145],"understanding":[68],"that":[69,121],"addresses":[70],"limitations.Our":[72],"ChuLo":[73],"groups":[74],"input":[75,94],"tokens":[76,108],"using":[77],"unsupervised":[78],"keyphrase":[79,84],"extraction,":[80],"emphasizing":[81],"semantically":[82],"important":[83,118],"based":[85],"chunks":[86],"retain":[88],"core":[89],"content":[91],"while":[92],"reducing":[93],"length.This":[95],"approach":[96],"minimizes":[97],"improves":[101],"efficiency":[103],"of":[104],"models.Preserving":[106],"all":[107],"understanding,":[112],"especially":[113],"token":[114,146],"classification":[115,141,147],"ensure":[120],"fine-grained":[122],"annotations,":[123],"which":[124],"depend":[125],"on":[126,137,161],"entire":[128],"sequence":[129],"context,":[130],"are":[131],"not":[132],"lost.We":[133],"evaluate":[134],"our":[135],"multiple":[138],"tasks":[142],"demonstrating":[149],"its":[150],"effectiveness":[151],"through":[152],"comprehensive":[153],"qualitative":[154],"quantitative":[156],"analysis.Our":[157],"implementation":[158],"open-sourced":[160],"GitHub":[162],"1":[163],".":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2025-10-10T00:00:00"}