{"id":"https://openalex.org/W4412377024","doi":"https://doi.org/10.1145/3726302.3730274","title":"Dense Retrieval for Low Resource languages - the Case of Amharic Language","display_name":"Dense Retrieval for Low Resource languages - the Case of Amharic Language","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377024","doi":"https://doi.org/10.1145/3726302.3730274"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730274","doi":"https://doi.org/10.1145/3726302.3730274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730274","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730274","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","observed_orcids":["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":["IT Doctoral Program, Addis Ababa University, Addis Ababa, Ethiopia"],"raw_orcid":"https://orcid.org/0000-0003-0599-262X","affiliations":[{"raw_affiliation_string":"IT Doctoral Program, Addis Ababa University, Addis Ababa, Ethiopia","institution_ids":["https://openalex.org/I4537092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074290191","display_name":"Moncef Garouani","orcid":"https://orcid.org/0000-0003-2528-441X","observed_orcids":["https://orcid.org/0000-0003-2528-441X"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Moncef Garouani","raw_affiliation_strings":["IRIT, UMR5505 CNRS, Univ. Toulouse Capitole, Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0003-2528-441X","affiliations":[{"raw_affiliation_string":"IRIT, UMR5505 CNRS, Univ. Toulouse Capitole, Toulouse, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029162303","display_name":"Serge Molina","orcid":"https://orcid.org/0009-0007-7894-7041","observed_orcids":["https://orcid.org/0009-0007-7894-7041"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Serge Molina","raw_affiliation_strings":["IRIT, UMR5505 CNRS, Univ. de Toulouse, Toulouse, France"],"raw_orcid":"https://orcid.org/0009-0007-7894-7041","affiliations":[{"raw_affiliation_string":"IRIT, UMR5505 CNRS, Univ. de Toulouse, Toulouse, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119061","https://openalex.org/I4405258862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035274820","display_name":"Josiane Mothe","orcid":"https://orcid.org/0000-0001-9273-2193","observed_orcids":["https://orcid.org/0000-0001-9273-2193"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Josiane Mothe","raw_affiliation_strings":["IRIT, UMR5505 CNRS, UT2J, Univ. de Toulouse, Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0001-9273-2193","affiliations":[{"raw_affiliation_string":"IRIT, UMR5505 CNRS, UT2J, Univ. de Toulouse, Toulouse, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14800523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3098","last_page":"3100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8866999745368958,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8866999745368958,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.10400000214576721,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.004699999932199717,"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/dense-retrieval","display_name":"dense retrieval","score":0.9929999709129333},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9300000071525574},{"id":"https://openalex.org/keywords/amharic","display_name":"Amharic language","score":0.9160000085830688},{"id":"https://openalex.org/keywords/sparse-retrieval","display_name":"sparse retrieval","score":0.6710000038146973},{"id":"https://openalex.org/keywords/training-dataset-construction","display_name":"training dataset construction","score":0.6340000033378601},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.6330000162124634},{"id":"https://openalex.org/keywords/multilingual-information-retrieval","display_name":"multilingual information retrieval","score":0.765999972820282}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9858078956604004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975614070892334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5684012770652771},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5297898650169373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3803569972515106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3328656852245331},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3309180736541748},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730274","doi":"https://doi.org/10.1145/3726302.3730274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730274","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05195625v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05195625","pdf_url":"https://hal.science/hal-05195625v1/document","source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2025, Padua, Italy. pp.3098-3100, ⟨10.1145/3726302.3730274⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730274","doi":"https://doi.org/10.1145/3726302.3730274","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730274","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730274","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4306980366","display_name":"General pUrpose dIalogue-based DigitAl iNformation acCEss","funder_award_id":"ANR-23-IAS1-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377024.pdf","grobid_xml":"https://content.openalex.org/works/W4412377024.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2069870183","https://openalex.org/W2963341956","https://openalex.org/W2981852735","https://openalex.org/W3034617741","https://openalex.org/W3101860695","https://openalex.org/W3217305727","https://openalex.org/W4284664419","https://openalex.org/W4285077564","https://openalex.org/W4288089799","https://openalex.org/W4327967184","https://openalex.org/W4385574290"],"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/W589849612","https://openalex.org/W3014460680"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"investigation":[4],"into":[5],"dense":[6,26,35],"retrieval":[7,27,38,54],"models":[8,28],"for":[9,56],"Amharic,":[10],"a":[11],"low-resource":[12,57],"language":[13],"spoken":[14],"by":[15,33],"more":[16],"than":[17],"120":[18],"million":[19],"people.We":[20],"constructed":[21],"training":[22],"datasets":[23],"tailored":[24],"to":[25],"and":[29,36,49],"evaluated":[30],"model":[31],"performance":[32],"comparing":[34],"sparse":[37],"approaches":[39],"on":[40],"Amharic":[41],"information":[42],"retrieval.The":[43],"study":[44],"also":[45],"highlights":[46],"the":[47],"challenges":[48],"efforts":[50],"involved":[51],"in":[52],"advancing":[53],"systems":[55],"languages.":[58]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2025-10-10T00:00:00"}