{"id":"https://openalex.org/W2052227241","doi":"https://doi.org/10.1145/1289600.1289602","title":"Adaptive text correction with Web-crawled domain-dependent dictionaries","display_name":"Adaptive text correction with Web-crawled domain-dependent dictionaries","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2052227241","doi":"https://doi.org/10.1145/1289600.1289602","mag":"2052227241"},"language":"en","primary_location":{"id":"doi:10.1145/1289600.1289602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1289600.1289602","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-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/A5110248832","display_name":"Christoph Ringlstetter","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christoph Ringlstetter","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109699155","display_name":"Klaus U. Schulz","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus U. Schulz","raw_affiliation_strings":["University of Munich, Munich, Germany","University of Munich, Munich, GERMANY#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"University of Munich, Munich, GERMANY#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114255303","display_name":"Stoyan Mihov","orcid":null},"institutions":[{"id":"https://openalex.org/I24768866","display_name":"Bulgarian Academy of Sciences","ror":"https://ror.org/01x8hew03","country_code":"BG","type":"government","lineage":["https://openalex.org/I24768866"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Stoyan Mihov","raw_affiliation_strings":["Bulgarian Academy of Sciences, Sofia, Bulgaria","[Bulgarian Academy of Sciences, Sofia, Bulgaria]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bulgarian Academy of Sciences, Sofia, Bulgaria","institution_ids":["https://openalex.org/I24768866"]},{"raw_affiliation_string":"[Bulgarian Academy of Sciences, Sofia, Bulgaria]","institution_ids":["https://openalex.org/I24768866"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4313,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85441543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":"4","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.996399998664856,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8781906366348267},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.7833449840545654},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6941472291946411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6312731504440308},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5757049322128296},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5410877466201782},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5379773378372192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333176851272583},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5037345290184021},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4581427276134491},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.4577521085739136},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19354462623596191},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1926385760307312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8781906366348267},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.7833449840545654},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6941472291946411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6312731504440308},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5757049322128296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5410877466201782},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5379773378372192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333176851272583},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5037345290184021},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4581427276134491},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.4577521085739136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19354462623596191},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1926385760307312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1289600.1289602","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1289600.1289602","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W27881537","https://openalex.org/W66690650","https://openalex.org/W170619969","https://openalex.org/W1508165687","https://openalex.org/W1549285799","https://openalex.org/W1620568205","https://openalex.org/W1647671624","https://openalex.org/W1897795992","https://openalex.org/W2004637830","https://openalex.org/W2007780422","https://openalex.org/W2010595692","https://openalex.org/W2024730980","https://openalex.org/W2061491895","https://openalex.org/W2065533756","https://openalex.org/W2066102695","https://openalex.org/W2066792529","https://openalex.org/W2071003614","https://openalex.org/W2083393647","https://openalex.org/W2099510384","https://openalex.org/W2100716182","https://openalex.org/W2109469864","https://openalex.org/W2111192396","https://openalex.org/W2111949691","https://openalex.org/W2113641473","https://openalex.org/W2116533968","https://openalex.org/W2117084652","https://openalex.org/W2141265687","https://openalex.org/W2142268730","https://openalex.org/W2158699664","https://openalex.org/W2596600410","https://openalex.org/W2603454388","https://openalex.org/W4241299755","https://openalex.org/W4251462924","https://openalex.org/W7071444332"],"related_works":["https://openalex.org/W2359001871","https://openalex.org/W1605371805","https://openalex.org/W3107474891","https://openalex.org/W2411679502","https://openalex.org/W2118172714","https://openalex.org/W2010576059","https://openalex.org/W2035154876","https://openalex.org/W2765960438","https://openalex.org/W138735333","https://openalex.org/W2052227241"],"abstract_inverted_index":{"For":[0,177],"the":[1,10,50,78,82,99,106,109,134,162,192,207],"success":[2],"of":[3,9,24,31,33,49,81,101,108,114,153,165],"lexical":[4],"text":[5,179],"correction,":[6,180],"high":[7],"coverage":[8,122],"underlying":[11],"background":[12],"dictionary":[13],"is":[14,52,195],"crucial.":[15],"Still,":[16],"most":[17],"correction":[18,61,138,175],"tools":[19],"are":[20,89,117,189],"built":[21],"on":[22],"top":[23],"static":[25,226],"dictionaries":[26,113,132,160],"that":[27,76,104,119,129,157],"represent":[28],"fixed":[29],"collections":[30,149],"expressions":[32],"a":[34,46,151,198],"given":[35,83],"language.":[36],"When":[37],"treating":[38],"texts":[39,168],"from":[40,150,219,225],"specific":[41],"domains":[42],"and":[43,59,146,191],"areas,":[44],"often":[45],"significant":[47,199],"part":[48],"vocabulary":[51,100,107],"missed.":[53],"In":[54,66],"this":[55,67,203],"situation,":[56],"both":[57],"automated":[58,174],"interactive":[60,178],"systems":[62],"produce":[63],"suboptimal":[64],"results.":[65],"article,":[68],"we":[69,205],"describe":[70],"strategies":[71],"for":[72,185,214],"crawling":[73],"Web":[74],"pages":[75,93,103],"fit":[77],"thematic":[79,154],"domain":[80],"input":[84,110],"text.":[85],"Special":[86],"filtering":[87],"techniques":[88],"introduced":[90],"to":[91],"avoid":[92],"with":[94,140,158],"many":[95],"orthographic":[96],"errors.":[97],"Collecting":[98],"filtered":[102],"meet":[105],"text,":[111],"dynamic":[112],"modest":[115],"size":[116],"obtained":[118,190,224],"reach":[120],"excellent":[121],"values.":[123],"A":[124],"tool":[125],"has":[126],"been":[127],"developed":[128],"automatically":[130],"crawls":[131],"in":[133,197],"indicated":[135],"way.":[136,200],"Our":[137],"experiments":[139],"crawled":[141,220],"dictionaries,":[142],"which":[143],"address":[144],"English":[145],"German":[147],"document":[148],"variety":[152],"fields,":[155],"show":[156],"these":[159],"even":[161],"error":[163],"rate":[164],"highly":[166],"accurate":[167],"can":[169],"be":[170],"reduced,":[171],"using":[172,210],"completely":[173],"methods.":[176],"more":[181],"sensible":[182],"candidate":[183],"sets":[184],"correcting":[186],"erroneous":[187],"words":[188],"manual":[193],"effort":[194],"reduced":[196],"To":[201],"complete":[202],"picture,":[204],"study":[206],"effect":[208],"when":[209],"word":[211],"trigram":[212,217],"models":[213,218],"correction.":[215],"Again,":[216],"corpora":[221],"outperform":[222],"those":[223],"corpora.":[227]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}