{"id":"https://openalex.org/W7168407387","doi":"https://doi.org/10.1145/3805712.3808575","title":"Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval","display_name":"Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168407387","doi":"https://doi.org/10.1145/3805712.3808575"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808575","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808575","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140847162","display_name":"Yongjie Zhou","orcid":"https://orcid.org/0009-0005-4170-288X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yongjie Zhou","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0009-0005-4170-288X","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140860585","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0726-5250"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0726-5250","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140835901","display_name":"Bevan Koopman","orcid":"https://orcid.org/0000-0001-5577-3391"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bevan Koopman","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia and CSIRO, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5577-3391","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia and CSIRO, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140887680","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia and Google, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0271-5563","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia and Google, Sydney, Australia","institution_ids":["https://openalex.org/I165143802","https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3081","last_page":"3091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.588699996471405},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5220999717712402},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.2994999885559082},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.2928999960422516},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.28060001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6294999718666077},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39559999108314514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808575","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808575","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2945127593","https://openalex.org/W4386576685","https://openalex.org/W4400529080","https://openalex.org/W4404783040"],"related_works":[],"abstract_inverted_index":{"Document":[0],"chunking":[1,16],"is":[2],"a":[3],"critical":[4],"preprocessing":[5],"step":[6],"in":[7],"dense":[8],"retrieval":[9],"systems,":[10],"yet":[11],"the":[12],"design":[13],"space":[14],"of":[15],"strategies":[17,37],"remains":[18],"poorly":[19],"understood.":[20],"Recent":[21],"research":[22],"has":[23],"proposed":[24],"several":[25],"concurrent":[26],"approaches,":[27],"including":[28],"LLM-guided":[29],"methods":[30,52],"(e.g.,":[31,38],"DenseX":[32],"and":[33,35,55],"LumberChunker)":[34],"contextualized":[36],"Late":[39],"Chunking),":[40],"which":[41],"generate":[42],"embeddings":[43],"before":[44],"segmentation":[45],"to":[46],"preserve":[47],"contextual":[48],"information.":[49],"However,":[50],"these":[51],"emerged":[53],"independently":[54],"were":[56],"evaluated":[57],"on":[58],"benchmarks":[59],"with":[60],"minimal":[61],"overlap,":[62],"making":[63],"direct":[64],"comparisons":[65],"difficult.":[66]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}
