{"id":"https://openalex.org/W3789944","doi":"https://doi.org/10.63317/5bnxfwtiwm6m","title":"Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler","display_name":"Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W3789944","doi":"https://doi.org/10.63317/5bnxfwtiwm6m","mag":"3789944"},"language":"en","primary_location":{"id":"doi:10.63317/5bnxfwtiwm6m","doi":"https://doi.org/10.63317/5bnxfwtiwm6m","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5bnxfwtiwm6m","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069886855","display_name":"Michael Gasser","orcid":"https://orcid.org/0000-0003-0390-1448","observed_orcids":["https://orcid.org/0000-0003-0390-1448"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Gasser","raw_affiliation_strings":["School of Informatics and Computing , Indiana University Bloomington , Indiana , USA 47405","\u2021Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing , Indiana University Bloomington , Indiana , USA 47405","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"raw_affiliation_string":"\u2021Indiana University","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069886855"],"corresponding_institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":0.7778,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65994334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","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"}}],"keywords":[{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8740000128746033},{"id":"https://openalex.org/keywords/lexicon-expansion","display_name":"lexicon expansion","score":0.765999972820282},{"id":"https://openalex.org/keywords/morphological-analyzer","display_name":"morphological analyzer","score":0.765999972820282},{"id":"https://openalex.org/keywords/web-crawling","display_name":"web crawling","score":0.6869999766349792},{"id":"https://openalex.org/keywords/tigrinya","display_name":"Tigrinya","score":0.953000009059906},{"id":"https://openalex.org/keywords/semitic-languages","display_name":"Semitic languages","score":0.8849999904632568},{"id":"https://openalex.org/keywords/root-extraction","display_name":"root extraction","score":0.890999972820282},{"id":"https://openalex.org/keywords/morphology-linguistics","display_name":"morphology (linguistics)","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.9112967252731323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242752552032471},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7694169282913208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6447973251342773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564121663570404},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5272076725959778},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.5097600817680359},{"id":"https://openalex.org/C158007255","wikidata":"https://www.wikidata.org/wiki/Q1055222","display_name":"Spectrum analyzer","level":2,"score":0.49599942564964294},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3987274169921875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2541901171207428},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.63317/5bnxfwtiwm6m","doi":"https://doi.org/10.63317/5bnxfwtiwm6m","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5bnxfwtiwm6m","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.9863","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.9863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.indiana.edu/l/www/ftp/gasser/lrec10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.563","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","raw_type":"text"},{"id":"mag:3789944","doi":null,"is_oa":false,"landing_page_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus","jufo-3","norway-2"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/5bnxfwtiwm6m","doi":"https://doi.org/10.63317/5bnxfwtiwm6m","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5bnxfwtiwm6m","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6499999761581421}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3789944.pdf","grobid_xml":"https://content.openalex.org/works/W3789944.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W24718583","https://openalex.org/W656726572","https://openalex.org/W2081084291","https://openalex.org/W2089440824"],"related_works":["https://openalex.org/W161449610","https://openalex.org/W3136358307","https://openalex.org/W2973003675","https://openalex.org/W3014896654","https://openalex.org/W148774201","https://openalex.org/W1517616193","https://openalex.org/W3029443751","https://openalex.org/W2380184856","https://openalex.org/W2252224218","https://openalex.org/W2496038891","https://openalex.org/W3016139085","https://openalex.org/W2328915052","https://openalex.org/W2406517398","https://openalex.org/W3024540984","https://openalex.org/W111840064","https://openalex.org/W1575919763","https://openalex.org/W3133942780","https://openalex.org/W3167912200","https://openalex.org/W2250200621","https://openalex.org/W2251374702"],"abstract_inverted_index":{"Resource-poor":[0],"languages":[1,54],"may":[2],"suffer":[3],"from":[4,84],"a":[5,39,45,56,73,95,104,128],"lack":[6],"of":[7,9,28,59,65,93,118,146],"any":[8],"the":[10,24,36,62,66,91,116,133,147],"basic":[11],"resources":[12,101],"that":[13,30,68,111,124,150],"are":[14,70],"fundamental":[15],"to":[16,80,115,152],"computational":[17],"linguistics,":[18],"including":[19],"an":[20],"adequate":[21],"digital":[22],"lexicon.Given":[23],"relatively":[25],"small":[26],"corpus":[27],"texts":[29],"exists":[31],"for":[32,102],"such":[33],"languages,":[34],"extending":[35],"lexicon":[37,134],"presents":[38],"challenge.Languages":[40],"with":[41,98],"complex":[42],"morphology":[43],"present":[44],"special":[46],"case,":[47],"however,":[48],"because":[49],"individual":[50],"words":[51,123],"in":[52,135],"these":[53],"provide":[55],"great":[57],"deal":[58],"information":[60],"about":[61],"grammatical":[63],"properties":[64],"roots":[67,83,141],"they":[69],"based":[71],"on.Given":[72],"morphological":[74,105],"analyzer,":[75],"it":[76],"is":[77,107,109,125],"even":[78],"possible":[79],"extract":[81],"novel":[82],"words.In":[85],"this":[86,112],"paper,":[87],"we":[88],"look":[89],"at":[90],"case":[92],"Tigrinya,":[94],"Semitic":[96],"language":[97],"limited":[99],"lexical":[100],"which":[103],"analyzer":[106,113],"available.It":[108],"shown":[110],"applied":[114],"list":[117],"more":[119],"than":[120],"200,000":[121],"Tigrinya":[122],"extracted":[126],"by":[127,138,143],"web":[129],"crawler":[130],"can":[131],"extend":[132],"two":[136],"ways,":[137],"adding":[139],"new":[140],"and":[142],"inferring":[144],"some":[145],"derivational":[148],"constraints":[149],"apply":[151],"known":[153],"roots.":[154]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}
