{"id":"https://openalex.org/W4414253714","doi":"https://doi.org/10.1007/978-3-032-04624-6_33","title":"DocAnnot - Accelerating the\u00a0Creation of\u00a0Key Information Extraction Datasets with\u00a0GenAI-Powered Auto-annotation","display_name":"DocAnnot - Accelerating the\u00a0Creation of\u00a0Key Information Extraction Datasets with\u00a0GenAI-Powered Auto-annotation","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4414253714","doi":"https://doi.org/10.1007/978-3-032-04624-6_33"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-04624-6_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04624-6_33","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064625651","display_name":"Siddartha Reddy","orcid":"https://orcid.org/0009-0007-0791-4808"},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siddartha Reddy","raw_affiliation_strings":["Phi Labs, Quantiphi, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0007-0791-4808","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi, Mumbai, India","institution_ids":["https://openalex.org/I4210098931"]}]},{"author_position":"middle","author":{"id":null,"display_name":"P. M. Harikrishnan","orcid":"https://orcid.org/0000-0003-1844-9503"},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. M. Harikrishnan","raw_affiliation_strings":["Phi Labs, Quantiphi, Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0003-1844-9503","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi, Mumbai, India","institution_ids":["https://openalex.org/I4210098931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104263127","display_name":"Goutham Vignesh","orcid":"https://orcid.org/0009-0009-7668-8482"},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goutham Vignesh","raw_affiliation_strings":["Phi Labs, Quantiphi, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0009-7668-8482","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi, Mumbai, India","institution_ids":["https://openalex.org/I4210098931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018325578","display_name":"Vikash Varun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Varun","raw_affiliation_strings":["Phi Labs, Quantiphi, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0005-3598-266X","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi, Mumbai, India","institution_ids":["https://openalex.org/I4210098931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043579228","display_name":"Vishal Vaddina","orcid":"https://orcid.org/0009-0005-0214-5056"},"institutions":[{"id":"https://openalex.org/I4210086932","display_name":"Glycemic Index Laboratories","ror":"https://ror.org/005a08r96","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210086932"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vishal Vaddina","raw_affiliation_strings":["Phi Labs, Quantiphi, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0005-0214-5056","affiliations":[{"raw_affiliation_string":"Phi Labs, Quantiphi, Toronto, Canada","institution_ids":["https://openalex.org/I4210086932"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064625651"],"corresponding_institution_ids":["https://openalex.org/I4210098931"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39910576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9940999746322632,"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":0.9883999824523926,"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/key","display_name":"Key (lock)","score":0.645799994468689},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.57669997215271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5501000285148621},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5440000295639038},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.541700005531311},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5360000133514404},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.48010000586509705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9156000018119812},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.645799994468689},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5360000133514404},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47429999709129333},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C72010251","wikidata":"https://www.wikidata.org/wiki/Q5265688","display_name":"Determinantal point process","level":4,"score":0.2734000086784363},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-04624-6_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04624-6_33","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3104953317","https://openalex.org/W3120043490","https://openalex.org/W3176851559","https://openalex.org/W4206428939","https://openalex.org/W4292937962","https://openalex.org/W4304013646","https://openalex.org/W4389520388","https://openalex.org/W4393154852","https://openalex.org/W4402335466","https://openalex.org/W4404783389"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}