{"id":"https://openalex.org/W3153221513","doi":"https://doi.org/10.1145/3404835.3463237","title":"Morphologically Annotated Amharic Text Corpora","display_name":"Morphologically Annotated Amharic Text Corpora","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153221513","doi":"https://doi.org/10.1145/3404835.3463237","mag":"3153221513"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://univ-tlse2.hal.science/hal-03362977","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088171082","display_name":"Tilahun Yeshambel","orcid":"https://orcid.org/0000-0003-0599-262X"},"institutions":[{"id":"https://openalex.org/I4537092","display_name":"Addis Ababa University","ror":"https://ror.org/038b8e254","country_code":"ET","type":"education","lineage":["https://openalex.org/I4537092"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Tilahun Yeshambel","raw_affiliation_strings":["Addis Ababa University, Addis Ababa , Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Addis Ababa University, Addis Ababa , Ethiopia","institution_ids":["https://openalex.org/I4537092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035274820","display_name":"Josiane Mothe","orcid":"https://orcid.org/0000-0001-9273-2193"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Josiane Mothe","raw_affiliation_strings":["Univ. de Toulouse, Toulouse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. de Toulouse, Toulouse, France","institution_ids":["https://openalex.org/I17866349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010912481","display_name":"Yaregal Assabie","orcid":"https://orcid.org/0000-0001-7591-9298"},"institutions":[{"id":"https://openalex.org/I4537092","display_name":"Addis Ababa University","ror":"https://ror.org/038b8e254","country_code":"ET","type":"education","lineage":["https://openalex.org/I4537092"]}],"countries":["ET"],"is_corresponding":false,"raw_author_name":"Yaregal Assabie","raw_affiliation_strings":["Addis Ababa University, Addis Ababa, Ethiopia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Addis Ababa University, Addis Ababa, Ethiopia","institution_ids":["https://openalex.org/I4537092"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75500852,"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":"2349","last_page":"2355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.9962999820709229,"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/T12090","display_name":"Language and cultural evolution","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9900000095367432,"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/amharic","display_name":"Amharic","score":0.9840832948684692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8156510591506958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6767100095748901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6054970026016235},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.513676106929779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.511315107345581},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4977312386035919},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.4533185660839081},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45022955536842346},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.42966118454933167},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18107008934020996},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06825968623161316}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9840832948684692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156510591506958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6767100095748901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6054970026016235},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.513676106929779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.511315107345581},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4977312386035919},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.4533185660839081},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45022955536842346},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.42966118454933167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18107008934020996},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06825968623161316},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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":2,"locations":[{"id":"doi:10.1145/3404835.3463237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03362977v1","is_oa":true,"landing_page_url":"https://univ-tlse2.hal.science/hal-03362977","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, Virtual Event Canada, France. pp.2349-2355, ⟨10.1145/3404835.3463237⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03362977v1","is_oa":true,"landing_page_url":"https://univ-tlse2.hal.science/hal-03362977","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, Virtual Event Canada, France. pp.2349-2355, ⟨10.1145/3404835.3463237⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1996824467","https://openalex.org/W2000832640","https://openalex.org/W2012376027","https://openalex.org/W2013985509","https://openalex.org/W2013997717","https://openalex.org/W2032459394","https://openalex.org/W2041538602","https://openalex.org/W2050794965","https://openalex.org/W2098162425","https://openalex.org/W2121605237","https://openalex.org/W2138958299","https://openalex.org/W2163566748","https://openalex.org/W2181694002","https://openalex.org/W2343954916","https://openalex.org/W2398936787","https://openalex.org/W2409439155","https://openalex.org/W2572041428","https://openalex.org/W2599005718","https://openalex.org/W2621900088","https://openalex.org/W2806886076","https://openalex.org/W2809268369","https://openalex.org/W2940643755","https://openalex.org/W2945133413","https://openalex.org/W3086559106","https://openalex.org/W3092786496","https://openalex.org/W3184486121","https://openalex.org/W6601355063"],"related_works":["https://openalex.org/W2071761836","https://openalex.org/W2068668614","https://openalex.org/W3121919928","https://openalex.org/W3083321524","https://openalex.org/W2103574067","https://openalex.org/W2393370774","https://openalex.org/W2078257655","https://openalex.org/W3144673486","https://openalex.org/W2779850188","https://openalex.org/W2955198597"],"abstract_inverted_index":{"In":[0],"information":[1,137],"retrieval":[2,138],"(IR),":[3],"documents":[4,23,27,40],"that":[5],"match":[6],"the":[7,34,39,69,75,83,125],"query":[8],"are":[9,45,57,65,143],"retrieved.":[10],"Search":[11],"engines":[12],"usually":[13],"conflate":[14],"word":[15,36],"variants":[16],"into":[17],"a":[18],"common":[19],"stem":[20],"when":[21],"indexing":[22],"because":[24],"queries":[25],"and":[26,92,101,115],"do":[28],"not":[29],"need":[30],"to":[31,41,47,85,132,145],"use":[32],"exactly":[33],"same":[35],"variant":[37],"for":[38,53,71,139],"be":[42,48,122],"relevant.":[43],"Stemmers":[44],"known":[46],"effective":[49],"in":[50,148],"many":[51],"languages":[52,59],"IR.":[54,150],"However,":[55],"there":[56],"still":[58],"where":[60],"stemmers":[61],"or":[62,136],"morphological":[63,134],"analyzers":[64,135],"missing;":[66],"this":[67],"is":[68,74,82],"case":[70],"Amharic":[72,109,149],"which":[73,120],"working":[76],"language":[77],"of":[78,95],"Ethiopia.":[79],"Morphological":[80],"analysis":[81],"key":[84],"derive":[86],"stems,":[87],"roots":[88],"(primary":[89],"lexical":[90],"units)":[91],"grammatical":[93],"markers":[94],"words":[96],"such":[97],"as":[98,111,113,128],"person,":[99],"tense":[100],"negation":[102],"markers.":[103],"This":[104],"paper":[105],"presents":[106],"morphologically":[107,117],"annotated":[108,118],"lexicons":[110],"well":[112],"stem-based":[114],"root-based":[116],"corpora":[119],"could":[121],"used":[123],"by":[124],"research":[126,147],"community":[127],"benchmark":[129],"collections":[130],"either":[131],"evaluate":[133],"Amharic.":[140],"Such":[141],"resources":[142],"believed":[144],"foster":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}