{"id":"https://openalex.org/W36770748","doi":null,"title":"Learning Compound Boundaries for Afrikaans Spelling Checking","display_name":"Learning Compound Boundaries for Afrikaans Spelling Checking","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W36770748","mag":"36770748"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.570.3571","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.570.3571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.puk.ac.za/opencms/export/PUK/html/fakulteite/lettere/ctext/Van_Huyssteen_x_Van_Zaanen_2004.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5010635728","display_name":"Gerhard B. Van Huyssteen","orcid":"https://orcid.org/0000-0003-1705-1747","observed_orcids":["https://orcid.org/0000-0003-1705-1747"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard B. Van Huyssteen","raw_affiliation_strings":["external organisation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"external organisation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086662281","display_name":"Menno M. van Zaanen","orcid":"https://orcid.org/0000-0003-1841-2444","observed_orcids":["https://orcid.org/0000-0003-1841-2444"]},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Menno M. Van Zaanen","raw_affiliation_strings":["(Tilburg University)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Tilburg University)","institution_ids":["https://openalex.org/I193700539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.00659755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12353","display_name":"Lexicography and Language Studies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/compound-word-recognition","display_name":"compound word recognition","score":0.5509999990463257},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.9750000238418579},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.9089999794960022},{"id":"https://openalex.org/keywords/compound-formation","display_name":"compound formation","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8836008906364441},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7456491589546204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6127872467041016},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5615813732147217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532816052436829},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5378180742263794},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.49218717217445374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4742397665977478},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.4566778540611267},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.42914479970932007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1443222463130951},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.10472062230110168},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09935873746871948},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.570.3571","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.570.3571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.puk.ac.za/opencms/export/PUK/html/fakulteite/lettere/ctext/Van_Huyssteen_x_Van_Zaanen_2004.pdf","raw_type":"text"},{"id":"pmh:uvt:oai:tilburguniversity.edu:publications/3bd465cf-df03-4220-b688-324d1210151e","doi":null,"is_oa":false,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/3bd465cf-df03-4220-b688-324d1210151e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Workshop on International Proofing Tools and Language Technologies","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W137095281","https://openalex.org/W413158773","https://openalex.org/W1483301097","https://openalex.org/W1513739421","https://openalex.org/W1576685422","https://openalex.org/W1786937534","https://openalex.org/W1972099155","https://openalex.org/W2015671670","https://openalex.org/W2125055259","https://openalex.org/W2338964549"],"related_works":["https://openalex.org/W2250250534","https://openalex.org/W137095281","https://openalex.org/W1513739421","https://openalex.org/W7095498047","https://openalex.org/W7100771582","https://openalex.org/W2035994018","https://openalex.org/W2115340050","https://openalex.org/W7096337698","https://openalex.org/W1523588979","https://openalex.org/W195433013"],"abstract_inverted_index":{"Current":[0],"spelling":[1,55],"checkers":[2],"for":[3,60,95],"Afrikaans":[4,32,54],"still":[5],"do":[6],"not":[7],"provide":[8],"full":[9],"access":[10],"to":[11,18,71,82],"desired":[12],"linguistic":[13],"performance,":[14],"especially":[15],"with":[16,37,146],"respect":[17],"high":[19,39],"lexical":[20,40],"recall":[21],"and":[22,64,101,152,159],"error":[23],"precision.":[24],"One":[25],"of":[26,103,116,149,154],"the":[27,50,99,104,123,128,132,139,150,155],"main":[28],"problems":[29,158],"is":[30,33,113],"that":[31,49,122],"an":[34,53],"agglutinative":[35],"language":[36],"a":[38,89,107,147],"generative":[41],"power":[42],"using":[43,110],"concatenative":[44],"compound":[45,84],"formation.":[46],"This":[47],"means":[48,66],"lexicon":[51],"in":[52],"checker":[56],"can":[57],"never":[58],"account":[59],"all":[61],"possible":[62,160],"compounds,":[63],"other":[65],"should":[67],"therefore":[68],"be":[69],"sought":[70],"recognise":[72],"valid":[73],"compounds.":[74],"In":[75],"this":[76],"article,":[77],"we":[78,87],"investigate":[79],"two":[80],"approaches":[81,118],"finding":[83],"boundaries.":[85],"First,":[86],"describe":[88],"longest":[90,124,140],"string-matching":[91,125,141],"algorithm,":[92],"which":[93],"searches":[94],"known":[96],"words":[97],"at":[98],"beginning":[100],"end":[102],"compound.":[105],"Next,":[106],"machine-learning":[108,129,133],"approach":[109,134],"decision":[111],"trees":[112],"implemented.":[114],"Results":[115],"both":[117],"are":[119],"presented,":[120],"indicating":[121],"algorithm":[126],"outperforms":[127],"approach.":[130],"However,":[131],"has":[135],"many":[136],"advantages":[137,151],"over":[138],"algorithm.":[142],"The":[143],"article":[144],"concludes":[145],"discussion":[148],"disadvantages":[153],"systems,":[156],"remaining":[157],"solutions.":[161],"1.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2016-06-24T00:00:00"}
