{"id":"https://openalex.org/W2168540514","doi":null,"title":"Infrastructure Components for Large-Scale Information Extraction Systems","display_name":"Infrastructure Components for Large-Scale Information Extraction Systems","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2168540514","mag":"2168540514"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.1324","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.1324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~wcohen/postscript/iaai-2003.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5051617344","display_name":"William W. Cohen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"William W. Cohen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051617344"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.082,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84004273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.6273999810218811,"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":0.6273999810218811,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.11140000075101852,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.05139999836683273,"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/information-extraction","display_name":"information extraction","score":0.7990000247955322},{"id":"https://openalex.org/keywords/system-architecture","display_name":"system architecture","score":0.7630000114440918},{"id":"https://openalex.org/keywords/blackboard-systems","display_name":"blackboard architecture","score":0.8360000252723694},{"id":"https://openalex.org/keywords/component-communication","display_name":"component communication","score":0.7820000052452087},{"id":"https://openalex.org/keywords/task-sequencing","display_name":"task sequencing","score":0.7160000205039978},{"id":"https://openalex.org/keywords/classifier-combination","display_name":"classifier combination","score":0.4129999876022339},{"id":"https://openalex.org/keywords/feature-computation","display_name":"feature computation","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985222339630127},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7045696377754211},{"id":"https://openalex.org/C157273737","wikidata":"https://www.wikidata.org/wiki/Q1753023","display_name":"Blackboard system","level":3,"score":0.6833897233009338},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6374474763870239},{"id":"https://openalex.org/C2778308757","wikidata":"https://www.wikidata.org/wiki/Q23601418","display_name":"Blackboard (design pattern)","level":2,"score":0.5769205093383789},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5412333607673645},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5118090510368347},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4939418435096741},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4603455066680908},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.4362730085849762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40190765261650085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3897441029548645},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17415088415145874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09865811467170715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08763039112091064},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.1324","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.1324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~wcohen/postscript/iaai-2003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.502.1804","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.502.1804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/IAAI/2003/IAAI03-010.pdf","raw_type":"text"},{"id":"mag:2168540514","doi":null,"is_oa":false,"landing_page_url":"https://aaaipress.org/Papers/IAAI/2003/IAAI03-010.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418918","display_name":"Innovative Applications of Artificial Intelligence","issn_l":"2154-8080","issn":["2154-8080"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Innovative Applications of Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5378999710083008}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W109947125","https://openalex.org/W125867323","https://openalex.org/W1500859230","https://openalex.org/W1549417407","https://openalex.org/W1585042987","https://openalex.org/W2022090818","https://openalex.org/W2033709196","https://openalex.org/W2036216970","https://openalex.org/W2038281398","https://openalex.org/W2046166587","https://openalex.org/W2061146398","https://openalex.org/W2067018993","https://openalex.org/W2074297512","https://openalex.org/W2147492008","https://openalex.org/W2148762016","https://openalex.org/W2164235596","https://openalex.org/W2164322797","https://openalex.org/W2168598710","https://openalex.org/W2168753596","https://openalex.org/W2168808732","https://openalex.org/W2169591950","https://openalex.org/W2170408876"],"related_works":["https://openalex.org/W2546543898","https://openalex.org/W7098244677","https://openalex.org/W7100068910","https://openalex.org/W6991842946","https://openalex.org/W168752003","https://openalex.org/W2060741887","https://openalex.org/W2135779000","https://openalex.org/W4229909500","https://openalex.org/W111277439","https://openalex.org/W7095555461"],"abstract_inverted_index":{"Large-scale":[0],"systems":[1,15,30,63],"for":[2,59,71,80],"information":[3,41,61],"extraction":[4,62],"include":[5],"many":[6,32],"different":[7],"classifiers":[8],"and":[9,25,45,75,88],"extractors.":[10],"Experience":[11],"in":[12,27,29],"building":[13],"such":[14],"shows":[16],"that":[17],"finding":[18],"an":[19,57],"appropriate":[20],"architecture":[21,58],"is":[22,36,64],"both":[23],"difficult":[24],"important:":[26],"partic-ular,":[28],"containing":[31],"learned":[33],"components,":[34,44,74],"it":[35],"important":[37],"to":[38,46],"cleanly":[39],"share":[40],"between":[42,73],"the":[43,49,52],"flexibly":[47],"sequence":[48],"actions":[50],"of":[51],"components.":[53],"In":[54],"this":[55],"paper,":[56],"large-scale":[60],"described,":[65],"based":[66],"a":[67,76],"light-weight":[68],"blackboard":[69],"system":[70,79],"communi-cation":[72],"declarative":[77],"control":[78],"automatically":[81],"sequencing":[82],"component-level":[83],"tasks":[84],"like":[85],"classification,":[86],"extraction,":[87],"feature":[89],"compu-tation.":[90]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2016-06-24T00:00:00"}