{"id":"https://openalex.org/W4206638272","doi":"https://doi.org/10.1109/ict4da53266.2021.9672229","title":"Impacts of Homophone Normalization on Semantic Models for Amharic","display_name":"Impacts of Homophone Normalization on Semantic Models for Amharic","publication_year":2021,"publication_date":"2021-11-22","ids":{"openalex":"https://openalex.org/W4206638272","doi":"https://doi.org/10.1109/ict4da53266.2021.9672229"},"language":"en","primary_location":{"id":"doi:10.1109/ict4da53266.2021.9672229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da53266.2021.9672229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","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/A5040546523","display_name":"Tadesse Destaw Belay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114501","display_name":"Wollo University","ror":"https://ror.org/01ktt8y73","country_code":"ET","type":"education","lineage":["https://openalex.org/I4210114501"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Tadesse Destaw Belay","raw_affiliation_strings":["College of Informatics, Wollo University, Kombolcha, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Informatics, Wollo University, Kombolcha, Ethiopia","institution_ids":["https://openalex.org/I4210114501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071390079","display_name":"Abinew Ali Ayele","orcid":"https://orcid.org/0000-0003-4686-5053"},"institutions":[{"id":"https://openalex.org/I57092466","display_name":"Bahir Dar University","ror":"https://ror.org/01670bg46","country_code":"ET","type":"education","lineage":["https://openalex.org/I57092466"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Abinew Ali Ayele","raw_affiliation_strings":["ICT4D Research Center, Bahir Dar University, Bahir dar, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT4D Research Center, Bahir Dar University, Bahir dar, Ethiopia","institution_ids":["https://openalex.org/I57092466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091709261","display_name":"Getie Gelaye","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Getie Gelaye","raw_affiliation_strings":["African Linguistics & Ethiopian Studies, Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"African Linguistics & Ethiopian Studies, Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039544387","display_name":"Seid Muhie Yimam","orcid":"https://orcid.org/0000-0002-8289-388X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Seid Muhie Yimam","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8486,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9278565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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/T10265","display_name":"Multilingual Education and Policy","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/amharic","display_name":"Amharic","score":0.9646110534667969},{"id":"https://openalex.org/keywords/homophone","display_name":"Homophone","score":0.6957025527954102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6650981307029724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5350030660629272},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5279625654220581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4478142261505127},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18896448612213135},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.061960577964782715}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9646110534667969},{"id":"https://openalex.org/C160253069","wikidata":"https://www.wikidata.org/wiki/Q221079","display_name":"Homophone","level":2,"score":0.6957025527954102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650981307029724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5350030660629272},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5279625654220581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478142261505127},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18896448612213135},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.061960577964782715},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ict4da53266.2021.9672229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da53266.2021.9672229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Information and Communication Technology for Development for Africa (ICT4DA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.7300000190734863,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1652017806","https://openalex.org/W1940872118","https://openalex.org/W2012026885","https://openalex.org/W2047490211","https://openalex.org/W2104712721","https://openalex.org/W2126260542","https://openalex.org/W2160055183","https://openalex.org/W2250630261","https://openalex.org/W2296725598","https://openalex.org/W2413241054","https://openalex.org/W2493916176","https://openalex.org/W2605682780","https://openalex.org/W2621900088","https://openalex.org/W2847467100","https://openalex.org/W2880875857","https://openalex.org/W2896457183","https://openalex.org/W2940643755","https://openalex.org/W2965373594","https://openalex.org/W2966765835","https://openalex.org/W2994268330","https://openalex.org/W3000398740","https://openalex.org/W3008133643","https://openalex.org/W3032316664","https://openalex.org/W3083321524","https://openalex.org/W3086559106","https://openalex.org/W3115267526","https://openalex.org/W4287113301","https://openalex.org/W4294170691","https://openalex.org/W4297801177","https://openalex.org/W6636510571","https://openalex.org/W6637086682","https://openalex.org/W6640362995","https://openalex.org/W6679220483","https://openalex.org/W6682691769","https://openalex.org/W6691434937","https://openalex.org/W6722332129","https://openalex.org/W6736367422","https://openalex.org/W6739531394","https://openalex.org/W6748304040","https://openalex.org/W6752788575","https://openalex.org/W6753068456","https://openalex.org/W6755207826","https://openalex.org/W6761413067","https://openalex.org/W6766673545","https://openalex.org/W6771487389","https://openalex.org/W6772680453","https://openalex.org/W6774608149","https://openalex.org/W6778833190","https://openalex.org/W6797753045"],"related_works":["https://openalex.org/W2071761836","https://openalex.org/W2068668614","https://openalex.org/W3121919928","https://openalex.org/W584933867","https://openalex.org/W2021956231","https://openalex.org/W4386930358","https://openalex.org/W1972048371","https://openalex.org/W4287822602","https://openalex.org/W4206638272","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Amharic":[0,22,40,69,117,143,180,195],"is":[1,43,120,128,140,150,253,272],"the":[2,12,17,29,65,75,85,97,107,111,142,148,167,189,220,227,245,257],"second-most":[3],"spoken":[4],"Semitic":[5],"language":[6,15],"after":[7],"Arabic":[8],"and":[9,73,83,90,138,183,192,263,286],"serves":[10],"as":[11,104],"official":[13],"working":[14],"of":[16,19,54,81,113,169,215,233,242],"government":[18],"Ethiopia.":[20],"In":[21],"writing,":[23],"there":[24,132],"are":[25,33,101,158],"different":[26,163,174],"characters":[27],"with":[28,230,284],"same":[30,108],"sound,":[31],"which":[32],"called":[34],"homophones.":[35],"The":[36,248],"current":[37],"trend":[38],"in":[39],"NLP":[41,118,196,258],"research":[42,277],"to":[44],"normalize":[45],"homophones":[46],"into":[47],"a":[48,135,201,205],"single":[49],"representation.":[50],"This":[51,93],"means,":[52],"instead":[53,80],"character":[55,70,76,86,127],"<sup":[56,59],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[57,60],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[58,61],"We":[62,187],"have":[63,106,162],"used":[64],"IPA":[66],"notation":[67],"for":[68,116,179,274],"transliteration,":[71],",":[72,74,82,84],"will":[77,87,133],"be":[78,88,134,282,292],"used;":[79],"replaced;":[89],"so":[91],"on.":[92],"was":[94],"done":[95],"by":[96,130],"assumption":[98],"that":[99,203,251,279],"they":[100,105,161],"repetitive":[102],"alphabets":[103],"sound.":[109],"However,":[110],"impact":[112],"homophone":[114,126,170,185],"normalization":[115,252,266,280],"applications":[119],"not":[121],"well":[122],"studied.":[123],"When":[124],"one":[125],"substituted":[129],"another,":[131],"meaning":[136],"change":[137],"it":[139,271],"against":[141],"writing":[144],"regulation.":[145],"For":[146,198,217,235,260],"example,":[147],"word":[149],"\u201cpoverty\u201d":[151],"while":[152,270],"means":[153],"\u201csalvage\u201d.":[154],"These":[155],"two":[156],"words":[157],"homophones,":[159],"but":[160],"meanings.":[164],"To":[165],"study":[166],"impacts":[168,269],"normalization,":[171],"we":[172,238],"develop":[173],"general-purpose":[175],"pre-trained":[176,190],"embedding":[177,208,225],"models":[178,191,229],"using":[181,244],"regular":[182,206,223],"normalized":[184,246],"characters.":[186],"fine-tune":[188],"build":[193],"some":[194],"applications.":[197,259],"PoS":[199,264],"tagging,":[200,265],"model":[202,209,221],"employs":[204],"FLAIR":[207],"performs":[210],"better,":[211],"achieving":[212],"an":[213,231,240],"F1-score":[214,232,241],"77%.":[216],"sentiment":[218,261],"analysis,":[219],"from":[222],"RoBERTa":[224],"outperforms":[226],"other":[228],"60%.":[234],"IR":[236],"systems,":[237],"achieve":[239],"90%":[243],"document.":[247],"results":[249],"show":[250],"highly":[254],"dependent":[255],"on":[256],"analysis":[262],"has":[267],"negative":[268],"essential":[273],"IR.":[275],"Our":[276],"indicates":[278],"should":[281,291],"applied":[283],"caution":[285],"more":[287],"effort":[288],"towards":[289],"standardization":[290],"given.":[293]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
