{"id":"https://openalex.org/W4412888450","doi":"https://doi.org/10.18653/v1/2025.findings-acl.543","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","display_name":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888450","doi":"https://doi.org/10.18653/v1/2025.findings-acl.543"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.543","pdf_url":"https://aclanthology.org/2025.findings-acl.543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.543.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106343200","display_name":"Kidist Amde Mekonnen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kidist Amde Mekonnen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181425","display_name":"Yosef Worku Alemneh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosef Worku Alemneh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8407,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90695974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10428","last_page":"10445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9890999794006348,"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":0.9890999794006348,"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/T10028","display_name":"Topic Modeling","score":0.9811999797821045,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9710000157356262,"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":0.989703893661499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779130220413208},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.641535758972168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6330607533454895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5657033920288086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570891499519348}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.989703893661499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779130220413208},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.641535758972168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6330607533454895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5657033920288086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570891499519348}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.543","pdf_url":"https://aclanthology.org/2025.findings-acl.543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/88204ae4-ffae-4bc8-8386-37b9b821b954","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/optimized-text-embedding-models-and-benchmarks-for-amharic-passage-retrieval(88204ae4-ffae-4bc8-8386-37b9b821b954).html","pdf_url":"https://pure.uva.nl/ws/files/306225055/2025.findings-acl.543.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.543","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.543","pdf_url":"https://aclanthology.org/2025.findings-acl.543.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2289169492","display_name":"Fairness and Intersectional Non-Discrimination in Human Recommendation","funder_award_id":"101070212","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5550786340","display_name":"Hybrid Intelligence (HI): augmenting human intellect","funder_award_id":"024.004.022","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6280615682","display_name":"Low Resource Chat-based Conversational Intelligence","funder_award_id":"NWA.1389.20.183","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6640760388","display_name":"Trustworthy AI-based Systems for Sustainable Growth","funder_award_id":"KICH3.LTP.20.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888450.pdf","grobid_xml":"https://content.openalex.org/works/W4412888450.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2071761836","https://openalex.org/W2068668614","https://openalex.org/W3121919928","https://openalex.org/W584933867","https://openalex.org/W3151869483","https://openalex.org/W2021956231","https://openalex.org/W4386930358","https://openalex.org/W1972048371","https://openalex.org/W4287822602","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Neural":[0],"retrieval":[1,40,97,119,124],"methods":[2],"using":[3],"transformerbased":[4],"pre-trained":[5,44],"language":[6],"models":[7,41,113],"have":[8],"advanced":[9],"multilingual":[10,71],"and":[11,30,47,62,117,135,154],"cross-lingual":[12],"retrieval.However,":[13],"their":[14],"effectiveness":[15,125],"for":[16],"lowresource,":[17],"morphologically":[18],"rich":[19],"languages":[20],"such":[21,80],"as":[22,81],"Amharic":[23,45],"remains":[24],"underexplored":[25],"due":[26],"to":[27,121],"data":[28],"scarcity":[29],"suboptimal":[31],"tokenization.We":[32],"address":[33],"this":[34],"gap":[35],"by":[36],"introducing":[37],"Amharic-specific":[38],"dense":[39,118],"based":[42],"on":[43],"BERT":[46],"RoBERTa":[48],"backbones.Our":[49],"proposed":[50,112],"RoBERTa-Base-Amharic-Embed":[51],"model":[52,98],"(110M":[53],"parameters)":[54],"achieves":[55,100],"a":[56,63,93],"17.6%":[57],"relative":[58],"improvement":[59],"in":[60,66,126,132,145],"MRR@10":[61,103],"9.86%":[64],"gain":[65],"Recall@10":[67],"over":[68,88],"the":[69,101,137],"strongest":[70],"baseline,":[72],"Arctic":[73],"Embed":[74],"2.0":[75],"(568M":[76],"parameters).More":[77],"compact":[78],"variants,":[79],"RoBERTa-Medium-Amharic-Embed":[82],"(42M),":[83],"remain":[84],"competitive":[85],"while":[86],"being":[87],"13\u00d7":[89],"smaller.Additionally,":[90],"we":[91,148],"train":[92],"ColBERT-based":[94],"late":[95],"interaction":[96],"that":[99],"highest":[102],"score":[104],"(0.843)":[105],"among":[106],"all":[107],"evaluated":[108],"models.We":[109],"benchmark":[110],"our":[111,151],"against":[114],"both":[115],"sparse":[116],"baselines":[120],"systematically":[122],"assess":[123],"Amharic.Our":[127],"analysis":[128],"highlights":[129],"key":[130],"challenges":[131],"low-resource":[133],"settings":[134],"underscores":[136],"importance":[138],"of":[139],"language-specific":[140],"adaptation.To":[141],"foster":[142],"future":[143],"research":[144],"lowresource":[146],"IR,":[147],"publicly":[149],"release":[150],"dataset,":[152],"codebase,":[153],"trained":[155],"models.":[156],"1":[157],"*":[158],"Equal":[159],"contribution.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}