{"id":"https://openalex.org/W4205559769","doi":"https://doi.org/10.1109/ict4da53266.2021.9672246","title":"Amharic Text Corpus based on Parts of Speech tagging and headwords","display_name":"Amharic Text Corpus based on Parts of Speech tagging and headwords","publication_year":2021,"publication_date":"2021-11-22","ids":{"openalex":"https://openalex.org/W4205559769","doi":"https://doi.org/10.1109/ict4da53266.2021.9672246"},"language":"en","primary_location":{"id":"doi:10.1109/ict4da53266.2021.9672246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da53266.2021.9672246","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":"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/A5068260603","display_name":"Tsegaye Abebe","orcid":null},"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":"Tsegaye Abebe","raw_affiliation_strings":["ICT4D reseach center, Bahir Dar Instititute of technology, Bahir Dar University, Bahir Dar, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT4D reseach center, Bahir Dar Instititute of technology, Bahir Dar University, Bahir Dar, Ethiopia","institution_ids":["https://openalex.org/I57092466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079210242","display_name":"Esubalew Alemneh","orcid":"https://orcid.org/0000-0002-1970-3537"},"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":"Esubalew Alemneh","raw_affiliation_strings":["ICT4D reseach center, Bahir Dar Instititute of technology, Bahir Dar University, Bahir Dar, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT4D reseach center, Bahir Dar Instititute of technology, Bahir Dar University, Bahir Dar, Ethiopia","institution_ids":["https://openalex.org/I57092466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57092466"],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44385176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9869999885559082,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/amharic","display_name":"Amharic","score":0.9737570881843567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076605796813965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6565006375312805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5925408601760864},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42848747968673706},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4237912595272064},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3104099631309509}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9737570881843567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076605796813965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6565006375312805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925408601760864},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42848747968673706},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4237912595272064},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3104099631309509}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ict4da53266.2021.9672246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ict4da53266.2021.9672246","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":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1410460","https://openalex.org/W350471488","https://openalex.org/W934716949","https://openalex.org/W1521626219","https://openalex.org/W1664671319","https://openalex.org/W2036771209","https://openalex.org/W2172028209","https://openalex.org/W2273742105","https://openalex.org/W2513235117","https://openalex.org/W2572041428","https://openalex.org/W2625465398","https://openalex.org/W2915774325","https://openalex.org/W2940643755","https://openalex.org/W2949791182","https://openalex.org/W3128757078","https://openalex.org/W4244461024","https://openalex.org/W4255862684","https://openalex.org/W6732013568"],"related_works":["https://openalex.org/W3028477281","https://openalex.org/W2195354","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W4311415364","https://openalex.org/W2772686614","https://openalex.org/W4387366498","https://openalex.org/W3175595715","https://openalex.org/W2152945827","https://openalex.org/W2250932133"],"abstract_inverted_index":{"Corpus":[0],"is":[1],"a":[2,108,174],"milestone":[3],"to":[4,9,80,223,250],"study":[5],"natural":[6],"languages":[7],"and":[8,41,51,75,107,116,146,158,194,218,230],"develop":[10],"various":[11,94],"tools":[12],"for":[13,45],"the":[14,26,33,63,99,165,182,225,236,245],"processing":[15],"of":[16,28,65,72,101,111,119,123,141,149,160,168,181,208,227,232],"human":[17],"languages.":[18],"Since,":[19],"few":[20,109],"studies":[21],"are":[22,36,121,136,185,212,241],"carried":[23],"out":[24],"on":[25,155],"development":[27],"Amharic":[29,57,176,187,196,247],"language":[30,203],"corpus":[31,59,198,234],"development,":[32],"existing":[34],"corpora":[35,211],"very":[37],"small":[38],"in":[39,98,190,214,235],"size":[40,231],"not":[42],"well":[43,48],"accessible":[44],"academicians":[46],"as":[47,49],"commercial":[50],"non-commercial":[52],"organizations.":[53],"This":[54],"paper":[55],"presents":[56],"text":[58,95,177,188,192,197,210,233,248],"developed":[60,173],"by":[61],"applying":[62],"processes":[64],"annotating":[66],"each":[67,77,169],"word":[68,79],"with":[69,200],"its":[70,81],"part":[71,140,148],"speech":[73,142,150],"tag":[74,134,143,151,206,228],"reducing":[76],"orthographic":[78,161,170],"headword":[82],"using":[83],"either":[84],"derivational":[85],"or":[86],"inflectional":[87],"process.":[88],"We":[89,126,221],"extracted":[90],"12,720":[91],"sentences":[92],"from":[93,130,138],"documents":[96],"collected":[97],"domain":[100],"proclamations.":[102],"Ethiopian":[103],"1987":[104],"E.C":[105],"constitution":[106],"policies":[110],"Amhara":[112],"regional":[113],"state,":[114],"Ethiopia":[115,120],"federal":[117],"government":[118],"some":[122],"those":[124,131],"documents.":[125],"found":[127],"331,728":[128],"tokens":[129],"sentences.":[132],"66":[133],"sets":[135,207,229],"compiled":[137],"base":[139],"set":[144,152],"classes":[145,153],"compound":[147],"based":[154],"different":[156],"factors":[157],"representation":[159],"words.":[162],"To":[163],"help":[164],"manual":[166],"annotation":[167],"word,":[171],"we":[172,240],"semi-automatic":[175,246],"tagger.":[178],"The":[179,205],"outputs":[180],"research":[183],"project":[184],"pre-processed":[186],"stored":[189],"plain":[191],"format":[193],"tagged":[195],"encoded":[199],"extensible":[201],"markup":[202],"format.":[204],"annotated":[209],"represented":[213],"both":[215],"Ge'ez":[216],"script":[217],"English":[219],"characters.":[220],"plan":[222],"increase":[224],"number":[226],"near":[237],"future.":[238],"Moreover,":[239],"working":[242],"towards":[243],"converting":[244],"tagger":[249],"full":[251],"automation.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}