{"id":"https://openalex.org/W4289751790","doi":"https://doi.org/10.1145/3219819.3219834","title":"Corpus Conversion Service","display_name":"Corpus Conversion Service","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W4289751790","doi":"https://doi.org/10.1145/3219819.3219834"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3219834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219834","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024778597","display_name":"Peter Staar","orcid":"https://orcid.org/0000-0002-8088-0823"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter W J Staar","raw_affiliation_strings":["IBM Research, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675415","display_name":"Michele Dolfi","orcid":"https://orcid.org/0000-0001-7216-8505"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michele Dolfi","raw_affiliation_strings":["IBM Research, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046722997","display_name":"Christoph Auer","orcid":"https://orcid.org/0000-0001-5761-0422"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christoph Auer","raw_affiliation_strings":["IBM Research, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110940665","display_name":"Costas Bekas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Costas Bekas","raw_affiliation_strings":["IBM Research, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210126328"],"apc_list":null,"apc_paid":null,"fwci":3.9429,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.95086947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"774","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9925000071525574,"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":0.87623530626297},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6713382005691528},{"id":"https://openalex.org/keywords/bitmap","display_name":"Bitmap","score":0.6610774397850037},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6354140043258667},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4812578856945038},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.439637154340744},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.43693336844444275},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4271789789199829},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35541146993637085},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3295094966888428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2673013508319855},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14409014582633972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87623530626297},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6713382005691528},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.6610774397850037},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6354140043258667},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4812578856945038},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.439637154340744},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.43693336844444275},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4271789789199829},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35541146993637085},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3295094966888428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2673013508319855},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14409014582633972},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3219819.3219834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219834","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.02284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.02284","pdf_url":"https://arxiv.org/pdf/1806.02284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3219819.3219834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219819.3219834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219819.3219834","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320335367","display_name":"National Center of Competence in Research Materials\u2019 Revolution: Computational Design and Discovery of Novel Materials","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289751790.pdf","grobid_xml":"https://content.openalex.org/works/W4289751790.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W99136341","https://openalex.org/W1536680647","https://openalex.org/W1877528278","https://openalex.org/W2102605133","https://openalex.org/W2124410444","https://openalex.org/W2570343428","https://openalex.org/W2911964244","https://openalex.org/W2953106684","https://openalex.org/W2963037989","https://openalex.org/W2990138404","https://openalex.org/W3106250896","https://openalex.org/W4289751790"],"related_works":["https://openalex.org/W2350456333","https://openalex.org/W2101993108","https://openalex.org/W2356608866","https://openalex.org/W2355840328","https://openalex.org/W1975966184","https://openalex.org/W2137246017","https://openalex.org/W2364393392","https://openalex.org/W3126935378","https://openalex.org/W2377096008","https://openalex.org/W2019887508"],"abstract_inverted_index":{"Over":[0],"the":[1,5,35,41,47,56,59,65,91,135,196],"past":[2],"few":[3],"decades,":[4],"amount":[6],"of":[7,43,58,67,119,134,151,173,183,198],"scientific":[8],"articles":[9],"and":[10,33,69,104,114,145,189,218],"technical":[11],"literature":[12],"has":[13],"increased":[14],"exponentially":[15],"in":[16,185,195],"size.":[17],"Consequently,":[18],"there":[19],"is":[20,137,163,211],"a":[21,79,97,124],"great":[22],"need":[23],"for":[24,225],"systems":[25],"that":[26,132,157],"can":[27,146],"ingest":[28,84],"these":[29,44],"documents":[30,45,85,106],"at":[31,86,169],"scale":[32],"make":[34,64],"contained":[36],"knowledge":[37],"discoverable.":[38],"Unfortunately,":[39],"both":[40,179],"format":[42,49],"(e.g.":[46,61],"PDF":[48,120],"or":[50,121],"bitmap":[51],"images)":[52],"as":[53,55],"well":[54],"presentation":[57],"data":[60,71],"complex":[62],"tables)":[63],"extraction":[66],"qualitative":[68],"quantitive":[70],"extremely":[72],"challenging.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,154],"present":[78],"modular,":[80],"cloud-based":[81],"platform":[82,210],"to":[83,102,123,140,160,178,202,205],"scale.":[87],"This":[88,175],"platform,":[89],"called":[90],"Corpus":[92],"Conversion":[93],"Service":[94],"(CCS),":[95],"implements":[96],"pipeline":[98],"which":[99],"allows":[100,176],"users":[101,224],"parse":[103],"annotate":[105],"(i.e.":[107],"collect":[108],"ground-truth),":[109],"train":[110],"machine-learning":[111,166],"classification":[112],"algorithms":[113,167],"ultimately":[115],"convert":[116],"any":[117],"type":[118],"bitmap-documents":[122],"structured":[125,206],"content":[126,203],"representation":[127],"format.":[128],"We":[129],"will":[130,155],"show":[131,156],"each":[133],"modules":[136],"scalable":[138],"due":[139],"an":[141],"asynchronous":[142],"microservice":[143],"architecture":[144],"therefore":[147],"handle":[148],"massive":[149],"amounts":[150,182],"documents.":[152],"Furthermore,":[153],"our":[158],"capability":[159],"gather":[161,180],"groundtruth":[162],"accelerated":[164],"by":[165,168],"least":[170],"one":[171],"order":[172],"magnitude.":[174],"us":[177],"large":[181],"ground-truth":[184],"very":[186,191],"little":[187],"time":[188],"obtain":[190],"good":[192],"precision/recall":[193],"metrics":[194],"range":[197],"99%":[199],"with":[200],"regard":[201],"conversion":[204],"output.":[207],"The":[208],"CCS":[209],"currently":[212],"deployed":[213],"on":[214],"IBM":[215],"internal":[216],"infrastructure":[217],"serving":[219],"more":[220],"than":[221],"250":[222],"active":[223],"knowledge-engineering":[226],"project":[227],"engagements.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-08-04T00:00:00"}