{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:07Z","timestamp":1784138647776,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Center for Inclusive Digital Transformation of Africa (CIDTA) and Afretec Network","award":["None"],"award-info":[{"award-number":["None"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808622","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3152-3158","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The Alignment Gap: A Benchmark Demonstrating the Lack of Cross-Lingual Mapping in Dialect-Specialized Language Models - The Case of Ehugbo"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5879-6322","authenticated-orcid":false,"given":"Ukachi Agnes","family":"Eze-Mbey","sequence":"first","affiliation":[{"name":"Carnegie Mellon University Africa, Kigali, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3240-6551","authenticated-orcid":false,"given":"Victor Tolulope","family":"Olufemi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Africa, Kigali, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9638-4323","authenticated-orcid":false,"given":"Athanase Biluge","family":"Bahizire","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Africa, Kigali, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9696-2372","authenticated-orcid":false,"given":"Mikel K.","family":"Ngueajio","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Africa, Kigali, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7530-9497","authenticated-orcid":false,"given":"Prasenjit","family":"Mitra","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Africa, Kigali, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.97"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00416"},{"key":"e_1_3_2_2_3_1","volume-title":"Towards zero-shot cross-lingual image retrieval and tagging. ArXiv, abs\/2109.07622","author":"Aggarwal Pranav","year":"2021","unstructured":"Pranav Aggarwal, Ritiz Tambi, and Ajinkya Kale. Towards zero-shot cross-lingual image retrieval and tagging. ArXiv, abs\/2109.07622, 2021."},{"key":"e_1_3_2_2_4_1","unstructured":"Jesujoba O. Alabi David Ifeoluwa Adelani Marius Mosbach and Dietrich Klakow. Adapting pre-trained language models to African languages via multilingual adaptive fine-tuning. In Nicoletta Calzolari Chu-Ren Huang Hansaem Kim James Pustejovsky Leo Wanner Key-Sun Choi Pum-Mo Ryu Hsin-Hsi Chen Lucia Donatelli Heng Ji Sadao Kurohashi Patrizia Paggio Nianwen Xue Seokhwan Kim Younggyun Hahm Zhong He Tony Kyungil Lee Enrico Santus Francis Bond and Seung-Hoon Na editors Proceedings of the 29th International Conference on Computational Linguistics pages 4336-4349 Gyeongju Republic of Korea October 2022. International Committee on Computational Linguistics."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"e_1_3_2_2_6_1","volume-title":"Inc., 2011","author":"Inc.","year":"1973","unstructured":"Biblica, Inc. The Holy Bible, New International Version. Biblica, Inc., 2011. Copyright \u00a9 1973, 1978, 1984, 2011 Biblica, Inc."},{"key":"e_1_3_2_2_7_1","volume-title":"Winning the language divide with AI. https:\/\/imminent.translated.com\/winning-the-language-divide-with-ai","author":"Translated Research Center","year":"2025","unstructured":"Translated Research Center. Winning the language divide with AI. https:\/\/imminent.translated.com\/winning-the-language-divide-with-ai, 2025."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/1613162.1613171"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171-4186, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Bonaventure F. P. Dossou Atnafu Lambebo Tonja Oreen Yousuf Salomey Osei Abigail Oppong Iyanuoluwa Shode Oluwabusayo Olufunke Awoyomi and Chris Emezue. AfroLM: A self-active learning-based multilingual pretrained language model for 23 African languages. In Angela Fan Iryna Gurevych Yufang Hou Zornitsa Kozareva Sasha Luccioni Nafise Sadat Moosavi Sujith Ravi Gyuwan Kim Roy Schwartz and Andreas R\u00fcckl\u00e9 editors Proceedings of the Third Workshop on Simple and Efficient Natural Language Processing (SustaiNLP) pages 52-64 Abu Dhabi United Arab Emirates (Hybrid) December 2022. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.sustainlp-1.11"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"e_1_3_2_2_13_1","volume-title":"\u00d6zyiu011it. What drives cross-lingual ranking? retrieval approaches with multilingual language models. arXiv preprint arXiv:2511.19324","author":"Goworek Roksana","year":"2025","unstructured":"Roksana Goworek, Olivia Macmillan-Scott, and Eda B. \u00d6zyiu011it. What drives cross-lingual ranking? retrieval approaches with multilingual language models. arXiv preprint arXiv:2511.19324, 2025."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.471"},{"key":"e_1_3_2_2_15_1","first-page":"148","volume-title":"Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval, NLPIR '24","author":"Kimera Richard","year":"2025","unstructured":"Richard Kimera, DongNyeong Heo, Daniela N. Rim, and Heeyoul Choi. Data augmentation with back translation for low resource languages: A case of english and luganda. In Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval, NLPIR '24, page 142\u2013148, New York, NY, USA, 2025. Association for Computing Machinery."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-022-09406-x"},{"key":"e_1_3_2_2_17_1","first-page":"440","volume-title":"HCI International 2022 \u2013 Late Breaking Papers: Interacting with EXtended Reality and Artificial Intelligence: 24th International Conference on Human-Computer Interaction, HCII","author":"Mikel","year":"2022","unstructured":"Mikel K. Ngueajio and Gloria Washington. Hey asr system! why aren't you more inclusive? automatic speech recognition systems' bias and proposed bias mitigation techniques. a literature review. In HCI International 2022 \u2013 Late Breaking Papers: Interacting with EXtended Reality and Artificial Intelligence: 24th International Conference on Human-Computer Interaction, HCII 2022, Virtual Event, June 26 \u2013 July 1, 2022, Proceedings, page 421\u2013440, Berlin, Heidelberg, 2022. Springer-Verlag."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02138-1"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.11"},{"key":"e_1_3_2_2_20_1","volume-title":"Stanford Human-Centered Artificial Intelligence (HAI)","author":"Pava Juan","year":"2025","unstructured":"Juan Pava, Caroline Meinhardt, Haifa Badi Uz Zaman, Toni Friedman, Sang T. Truong, Daniel Zhang, Elena Cryst, Vukosi Marivate, and Sanmi Koyejo. Mind the (language) gap: Mapping the challenges of LLM development in low-resource language contexts. Technical report, Stanford Human-Centered Artificial Intelligence (HAI), April 2025."},{"key":"e_1_3_2_2_21_1","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, pages 8748-8763. PMLR, 2021."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953015"},{"key":"e_1_3_2_2_23_1","volume-title":"Literacy Development, the dEhugbo Literacy Development, the Literacy, and Bible Translation Project. Badibduldu Ns\u1e5b Agba Ohdudu Na Okwu dEhugbo. Bible translation","author":"Translation Trust Nigeria Bible","year":"2024","unstructured":"Nigeria Bible Translation Trust, the dEhugbo Initiative on Mother Tongue, Literacy Development, the dEhugbo Literacy Development, the Literacy, and Bible Translation Project. Badibduldu Ns\u1e5b Agba Ohdudu Na Okwu dEhugbo. Bible translation, 2024. First publication of the dEhugbo New Testament."},{"issue":"86","key":"e_1_3_2_2_24_1","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 9(86):2579-2605, 2008.","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:12:31Z","timestamp":1784135551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":24,"alternative-id":["10.1145\/3805712.3808622","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808622","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}