{"id":"https://openalex.org/W2009102799","doi":"https://doi.org/10.1145/1600193.1600237","title":"A panlingual anomalous text detector","display_name":"A panlingual anomalous text detector","publication_year":2009,"publication_date":"2009-09-16","ids":{"openalex":"https://openalex.org/W2009102799","doi":"https://doi.org/10.1145/1600193.1600237","mag":"2009102799"},"language":"en","primary_location":{"id":"doi:10.1145/1600193.1600237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078560039","display_name":"Ashok C. Popat","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashok C. Popat","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078560039"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.7311,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68181173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816684365272522},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7230733036994934},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.706979513168335},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5984545350074768},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.569650411605835},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5365958213806152},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5104802846908569},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4843810498714447},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.45016273856163025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4187777042388916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4030541479587555},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1100437343120575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816684365272522},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7230733036994934},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.706979513168335},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5984545350074768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.569650411605835},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5365958213806152},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5104802846908569},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4843810498714447},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.45016273856163025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4187777042388916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4030541479587555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1100437343120575},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1600193.1600237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1600193.1600237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W27881537","https://openalex.org/W123500707","https://openalex.org/W1981367467","https://openalex.org/W2045566081","https://openalex.org/W2063420976","https://openalex.org/W2118996379","https://openalex.org/W2124379907","https://openalex.org/W2135771747","https://openalex.org/W6678568454","https://openalex.org/W7047636377"],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2374093222","https://openalex.org/W2359533638"],"abstract_inverted_index":{"In":[0],"a":[1,23,89],"large-scale":[2],"book":[3,142],"scanning":[4],"operation,":[5],"material":[6],"can":[7,46],"vary":[8],"widely":[9],"in":[10,26],"language,":[11],"script,":[12],"genre,":[13],"domain,":[14],"print":[15],"quality,":[16],"and":[17,38,61,100,108,133],"other":[18],"factors,":[19],"giving":[20],"rise":[21],"to":[22,34,70],"corresponding":[24],"variability":[25],"the":[27,73,79,138],"OCRed":[28],"text.":[29],"It":[30],"is":[31,68,114],"often":[32],"desirable":[33],"automatically":[35],"detect":[36],"errorful":[37],"otherwise":[39,109],"anomalous":[40],"text":[41],"segments,":[42],"so":[43],"that":[44,72,85,94,101,105,116],"they":[45],"be":[47,76],"filtered":[48],"out":[49],"or":[50],"appropriately":[51],"flagged,":[52],"for":[53],"such":[54,64],"applications":[55],"as":[56],"indexing,":[57],"mining,":[58],"analyzing,":[59],"displaying,":[60],"selectively":[62],"re-processing":[63],"data.":[65],"Moreover,":[66],"it":[67,86,95,102],"advantageous":[69],"require":[71],"automated":[74],"detector":[75],"independent":[77],"of":[78,92,124,140],"underlying":[80],"OCR":[81],"engine":[82],"(or":[83],"engines),":[84],"work":[87],"over":[88],"broad":[90],"range":[91],"languages,":[93],"seamlessly":[96],"handle":[97],"mixed-language":[98],"material,":[99],"accommodate":[103],"documents":[104],"contain":[106],"domain-specific":[107],"rare":[110],"terminology.":[111],"A":[112],"technique":[113],"presented":[115],"satisfies":[117],"these":[118],"requirements,":[119],"using":[120],"an":[121],"adaptive":[122],"mixture":[123],"character-level":[125],"N-gram":[126],"language":[127],"models.":[128],"Its":[129],"design,":[130],"training,":[131],"implementation,":[132],"evaluation":[134],"are":[135],"described":[136],"within":[137],"context":[139],"high-volume":[141],"scanning.":[143]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}