{"id":"https://openalex.org/W4411550028","doi":"https://doi.org/10.1145/3701716.3715309","title":"Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents","display_name":"Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411550028","doi":"https://doi.org/10.1145/3701716.3715309"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715309","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073178764","display_name":"Qiang Sun","orcid":"https://orcid.org/0000-0002-4445-0025"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qiang Sun","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4445-0025","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071941416","display_name":"Yuanyi Luo","orcid":"https://orcid.org/0000-0001-7658-8451"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyi Luo","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-7658-8451","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045618474","display_name":"W. J. Zhang","orcid":"https://orcid.org/0009-0000-5196-8562"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenxiao Zhang","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0009-0000-5196-8562","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701504","display_name":"Sirui Li","orcid":"https://orcid.org/0000-0002-2504-3790"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sirui Li","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2504-3790","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104322891","display_name":"Jichunyang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jichunyang Li","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0009-0008-3075-3739","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Niu","orcid":"https://orcid.org/0009-0009-3357-6130"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kai Niu","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0009-0009-3357-6130","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083626219","display_name":"Xiangrui Kong","orcid":"https://orcid.org/0000-0001-5066-1294"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiangrui Kong","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5066-1294","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["The University of Western Australia, Perth, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7409-0948","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073178764"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":6.2854,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96078103,"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":"801","last_page":"804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9995999932289124,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9995999932289124,"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":0.9988999962806702,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735348641872406},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6013889312744141},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4884911775588989},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41266074776649475},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3686434030532837},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2288873791694641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735348641872406},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6013889312744141},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4884911775588989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41266074776649475},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3686434030532837},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2288873791694641}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411550028.pdf","grobid_xml":"https://content.openalex.org/works/W4411550028.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3027879771","https://openalex.org/W4388144143","https://openalex.org/W4388144297","https://openalex.org/W4401754921","https://openalex.org/W4402950921","https://openalex.org/W6959643953"],"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":{"Enterprises":[0],"generate":[1],"vast":[2],"amounts":[3],"of":[4,166,179,192],"unstructured":[5,70],"documents,":[6],"posing":[7],"challenges":[8],"for":[9,21,130,147],"knowledge":[10,194,204],"extraction":[11],"and":[12,30,85,115,123,144,153,161,177,198],"representation.":[13],"Large":[14],"language":[15],"models":[16,146],"(LLMs)":[17],"offer":[18],"strong":[19],"potential":[20],"processing":[22,77],"such":[23],"data":[24,50],"but":[25],"struggle":[26],"with":[27,97,138,189],"factual":[28],"accuracy":[29],"provenance.":[31],"Knowledge":[32],"graphs":[33],"(KGs)":[34],"provide":[35],"a":[36,52,61,94,101,109,117],"structured":[37],"framework":[38,63],"to":[39,64,79,157],"address":[40,55],"these":[41],"limitations":[42],"[6],":[43],"yet":[44],"constructing":[45],"high-quality":[46,66,203],"KGs":[47,67],"from":[48,68],"heterogeneous":[49],"remains":[51],"challenge.":[53],"To":[54],"this":[56],"issue,":[57],"we":[58],"present":[59],"Docs2KG,":[60],"modular":[62],"build":[65],"diverse":[69],"documents.":[71],"We":[72],"first":[73],"employs":[74],"state-of-the-art":[75],"document":[76,105,113],"techniques":[78],"extract":[80],"textual":[81],"content,":[82],"tabular":[83],"data,":[84],"figures.":[86],"The":[87],"extracted":[88],"information":[89],"is":[90,168,184],"then":[91],"unified":[92],"into":[93],"multifaceted":[95],"KG":[96,103,111,119],"three":[98],"aspects:":[99],"(1)":[100],"Layout":[102],"capturing":[104],"structural":[106],"hierarchies,":[107],"(2)":[108],"Metadata":[110],"preserving":[112],"properties,":[114],"(3)":[116],"Semantic":[118,131],"representing":[120],"domain-specific":[121],"entities":[122],"relationships.":[124],"Docs2KG":[125,167,183],"supports":[126],"multiple":[127],"construction":[128,196],"paradigms":[129],"KG:":[132],"ontology-based":[133],"approaches,":[134],"hybrid":[135],"NLP":[136],"pipelines":[137],"LLM":[139],"verification,":[140],"LLM-guided":[141],"ontology":[142],"generation,":[143],"specialized":[145],"named":[148],"entity":[149],"recognition,":[150],"event":[151],"extraction,":[152],"causal":[154],"relationship":[155],"identification":[156],"enhance":[158],"semantic":[159],"coverage":[160],"accuracy.":[162],"A":[163],"key":[164],"feature":[165],"its":[169],"human-in-the-loop":[170],"verification":[171],"interface,":[172],"enabling":[173],"iterative":[174],"quality":[175],"assessment":[176],"refinement":[178],"the":[180,190],"resulting":[181],"KGs.":[182],"openly":[185],"available":[186],"at":[187],"https://docs2kg.ai4wa.com,":[188],"aim":[191],"advancing":[193],"graph":[195,205],"research":[197],"accelerating":[199],"enterprise":[200],"applications":[201],"through":[202],"construction.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
