{"id":"https://openalex.org/W2065303853","doi":"https://doi.org/10.1145/1860559.1860624","title":"On helmholtz's principle for documents processing","display_name":"On helmholtz's principle for documents processing","publication_year":2010,"publication_date":"2010-09-21","ids":{"openalex":"https://openalex.org/W2065303853","doi":"https://doi.org/10.1145/1860559.1860624","mag":"2065303853"},"language":"en","primary_location":{"id":"doi:10.1145/1860559.1860624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"article","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/A5091025769","display_name":"Alexander Balinsky","orcid":"https://orcid.org/0000-0002-8151-4462"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alexander A. Balinsky","raw_affiliation_strings":["Cardiff School of Mathematics, Cardiff, United Kingdom","Cardiff School of Mathematics, Cardiff, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Cardiff School of Mathematics, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"Cardiff School of Mathematics, Cardiff, United Kingdom#TAB#","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080473462","display_name":"Helen Balinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]},{"id":"https://openalex.org/I4210156325","display_name":"Hewlett-Packard (United Kingdom)","ror":"https://ror.org/05g4mtv59","country_code":"GB","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210156325"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Helen Y. Balinsky","raw_affiliation_strings":["Hewlett-Packard, Bristol, United Kingdom","Hewlett-Packard, Bristol , United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard, Bristol, United Kingdom","institution_ids":["https://openalex.org/I4210156325"]},{"raw_affiliation_string":"Hewlett-Packard, Bristol , United Kingdom#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022519243","display_name":"Steven J. Simske","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven J. Simske","raw_affiliation_strings":["Hewlett-Packard , Fort Collins, CO, USA","Hewlett-Packard , Fort Collins , CO, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard , Fort Collins, CO, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard , Fort Collins , CO, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091025769"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":3.7563,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93328187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.986299991607666,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8015813827514648},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.577582597732544},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.5469645261764526},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5114489793777466},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5000548362731934},{"id":"https://openalex.org/keywords/helmholtz-free-energy","display_name":"Helmholtz free energy","score":0.48298707604408264},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4626838266849518},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44908612966537476},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4458586871623993},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.44075486063957214},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.353310763835907},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.30934107303619385},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18890395760536194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015813827514648},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.577582597732544},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.5469645261764526},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5114489793777466},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5000548362731934},{"id":"https://openalex.org/C27592594","wikidata":"https://www.wikidata.org/wiki/Q865821","display_name":"Helmholtz free energy","level":2,"score":0.48298707604408264},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4626838266849518},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44908612966537476},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4458586871623993},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.44075486063957214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.353310763835907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30934107303619385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18890395760536194},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1860559.1860624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1860559.1860624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:24433","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/24433/","pdf_url":null,"source":{"id":"https://openalex.org/S7407055383","display_name":"ORCA Online Research @Cardiff","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1447066968","https://openalex.org/W1513966746","https://openalex.org/W1533452257","https://openalex.org/W2024932032","https://openalex.org/W2026302857","https://openalex.org/W2144211451","https://openalex.org/W3012483050","https://openalex.org/W4293052488"],"related_works":["https://openalex.org/W2023567082","https://openalex.org/W1993099704","https://openalex.org/W2240262858","https://openalex.org/W4283768689","https://openalex.org/W4312055747","https://openalex.org/W2619791004","https://openalex.org/W2066380224","https://openalex.org/W1968750695","https://openalex.org/W3174953199","https://openalex.org/W4385504528"],"abstract_inverted_index":{"Keyword":[0],"extraction":[1,29],"is":[2,46,49],"a":[3,34,92],"fundamental":[4],"problem":[5,72],"in":[6,41],"text":[7],"data":[8,42],"mining":[9],"and":[10,25,44,56,79],"document":[11,17],"processing.":[12],"A":[13],"large":[14],"number":[15],"of":[16,27,66,73,94,96,107],"processing":[18,55],"applications":[19],"directly":[20],"depend":[21],"on":[22,51,58,110],"the":[23,59,63,71,97,105],"quality":[24],"speed":[26],"keyword":[28],"algorithms.":[30],"In":[31],"this":[32],"article,":[33],"novel":[35],"approach":[36],"to":[37,70,82,103],"rapid":[38],"change":[39],"detection":[40],"stream":[43],"documents":[45],"developed.":[47],"It":[48],"based":[50],"ideas":[52],"from":[53,62],"image":[54],"especially":[57],"Helmholtz":[60],"Principle":[61],"Gestalt":[64],"Theory":[65],"human":[67],"perception.":[68],"Applied":[69],"keywords":[74,85,98,108],"extraction,":[75],"it":[76],"delivers":[77],"fast":[78],"effective":[80],"tools":[81],"identify":[83],"meaningful":[84],"using":[86],"parameter-free":[87],"methods.":[88],"We":[89],"also":[90],"define":[91],"level":[93],"meaningfulness":[95],"which":[99],"can":[100],"be":[101],"used":[102],"modify":[104],"set":[106],"depending":[109],"application":[111],"needs.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}