{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:48:28Z","timestamp":1784836108511,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Data Science Centre, University of Amsterdam"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3658925","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T09:14:21Z","timestamp":1717578861000},"page":"562-572","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Tackling Language Modelling Bias in Support of Linguistic Diversity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3868-1740","authenticated-orcid":false,"given":"G\u00e1bor","family":"Bella","sequence":"first","affiliation":[{"name":"Lab-STICC, CNRS UMR 6285, IMT Atlantique, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2719-9721","authenticated-orcid":false,"given":"Paula","family":"Helm","sequence":"additional","affiliation":[{"name":"Faculty of Humanities, University of Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2457-3335","authenticated-orcid":false,"given":"Gertraud","family":"Koch","sequence":"additional","affiliation":[{"name":"Institute of Anthropological Studies on Culture and History, University of Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-6150","authenticated-orcid":false,"given":"Fausto","family":"Giunchiglia","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1250"},{"key":"e_1_3_2_1_2_1","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization Jade Goldstein Alon Lavie Chin-Yew Lin and Clare Voss (Eds.). Association for Computational Linguistics Ann Arbor Michigan 65\u201372. https:\/\/aclanthology.org\/W05-0909"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 10th global WordNet conference. 238\u2013244","author":"Batsuren Khuyagbaatar","year":"2019","unstructured":"Khuyagbaatar Batsuren, Amarsanaa Ganbold, Altangerel Chagnaa, and Fausto Giunchiglia. 2019. Building the mongolian wordnet. In Proceedings of the 10th global WordNet conference. 238\u2013244."},{"key":"e_1_3_2_1_4_1","unstructured":"Khuyagbaatar Batsuren Ekaterina Vylomova Verna Dankers Tsetsuukhei Delgerbaatar Omri Uzan Yuval Pinter and G\u00e1bor Bella. 2024. Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge. arxiv:2404.13292\u00a0[cs.CL]"},{"key":"e_1_3_2_1_5_1","volume-title":"The Social Power of Algorithms. Information","author":"Beer David","year":"2017","unstructured":"David Beer. 2017. The Social Power of Algorithms. Information, Communication & Society 20, 1 (2017)."},{"key":"e_1_3_2_1_6_1","volume-title":"Linguistic Diversity and Bias in Online Dictionaries","author":"Bella G\u00e1bor","unstructured":"G\u00e1bor Bella, Khuyagbaatar Batsuren, Temuulen Khishigsuren, and Fausto Giunchiglia. 2022. Linguistic Diversity and Bias in Online Dictionaries. University of Bayreuth African Studies Online (2022), 173."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.15"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference. 2812\u20132818","author":"Bella G\u00e1bor","year":"2020","unstructured":"G\u00e1bor Bella, Fiona McNeill, Rody Gorman, Caoimh\u00edn\u00a0\u00d3 Donna\u00edle, Kirsty MacDonald, Yamini Chandrashekar, Abed\u00a0Alhakim Freihat, and Fausto Giunchiglia. 2020. A major wordnet for a minority language: Scottish Gaelic. In Proceedings of The 12th Language Resources and Evaluation Conference. 2812\u20132818."},{"key":"e_1_3_2_1_9_1","volume-title":"On achieving and evaluating language-independence in NLP. Linguistic Issues in Language Technology 6","author":"Bender M","year":"2011","unstructured":"Emily\u00a0M Bender. 2011. On achieving and evaluating language-independence in NLP. Linguistic Issues in Language Technology 6 (2011)."},{"key":"e_1_3_2_1_10_1","volume-title":"IndoWordNet. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910)","author":"Bhattacharyya Pushpak","year":"2010","unstructured":"Pushpak Bhattacharyya. 2010. IndoWordNet. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.313"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.539"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"e_1_3_2_1_14_1","volume-title":"Demographic dialectal variation in social media: A case study of African-American English. arXiv preprint arXiv:1608.08868","author":"Blodgett Su\u00a0Lin","year":"2016","unstructured":"Su\u00a0Lin Blodgett, Lisa Green, and Brendan O\u2019Connor. 2016. Demographic dialectal variation in social media: A case study of African-American English. arXiv preprint arXiv:1608.08868 (2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1352\u20131362","author":"Bond Francis","year":"2013","unstructured":"Francis Bond and Ryan Foster. 2013. Linking and extending an open multilingual wordnet. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1352\u20131362."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association","author":"Bond Francis","year":"2020","unstructured":"Francis Bond, Luis Morgado\u00a0da Costa, Michael\u00a0Wayne Goodman, John\u00a0Philip McCrae, and Ahti Lohk. 2020. Some Issues with Building a Multilingual Wordnet. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 3189\u20133197. https:\/\/aclanthology.org\/2020.lrec-1.390"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association","author":"Chandran\u00a0Nair Nandu","year":"2022","unstructured":"Nandu Chandran\u00a0Nair, Rajendran\u00a0S. Velayuthan, Yamini Chandrashekar, G\u00e1bor Bella, and Fausto Giunchiglia. 2022. IndoUKC: A Concept-Centered Indian Multilingual Lexical Resource. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 2833\u20132840. https:\/\/aclanthology.org\/2022.lrec-1.303"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/11952.107"},{"key":"e_1_3_2_1_19_1","volume-title":"Advancing the Arabic WordNet: Elevating Content Quality. In 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT), LREC-COLING.","author":"Freihat Abed\u00a0Alhakim","year":"2024","unstructured":"Abed\u00a0Alhakim Freihat, Hadi Khalilia, G\u00e1bor Bella, and Fausto Giunchiglia. 2024. Advancing the Arabic WordNet: Elevating Content Quality. In 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT), LREC-COLING."},{"key":"e_1_3_2_1_20_1","volume-title":"Value sensitive design: Theory and methods","author":"Friedman Batya","year":"2002","unstructured":"Batya Friedman, Peter Kahn, and Alan Borning. 2002. Value sensitive design: Theory and methods. University of Washington technical report 2, 8 (2002)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/230538.230561"},{"key":"e_1_3_2_1_22_1","volume-title":"Is an Oxymoron","author":"Gitelman Lisa","unstructured":"Lisa Gitelman. 2013. \u201cRaw Data\u201d Is an Oxymoron. MIT Press, Cambridge, MA, USA."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Fausto Giunchiglia Khuyagbaatar Batsuren and Gabor Bella. 2017. Understanding and Exploiting Language Diversity.. In IJCAI. 4009\u20134017.","DOI":"10.24963\/ijcai.2017\/560"},{"key":"e_1_3_2_1_24_1","volume-title":"Representing interlingual meaning in lexical databases. Artificial Intelligence Review","author":"Giunchiglia Fausto","year":"2023","unstructured":"Fausto Giunchiglia, G\u00e1bor Bella, Nandu\u00a0C Nair, Yang Chi, and Hao Xu. 2023. Representing interlingual meaning in lexical databases. Artificial Intelligence Review (2023), 1\u201317."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.2307\/410659"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1956.11659599"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.2307\/3178066"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01064504"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-023-09742-6"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534149"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.396"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753522"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.560"},{"key":"e_1_3_2_1_34_1","volume-title":"The world color survey","author":"Kay Paul","unstructured":"Paul Kay, Brent Berlin, Luisa Maffi, William\u00a0R Merrifield, and Richard Cook. 2009. The world color survey. CSLI Publications Stanford, CA."},{"key":"e_1_3_2_1_35_1","volume-title":"Lexical diversity in kinship across languages and dialects. Frontiers in Psychology 14","author":"Khalilia Hadi","year":"2023","unstructured":"Hadi Khalilia, G\u00e1bor Bella, Abed\u00a0Alhakim Freihat, Shandy Darma, and Fausto Giunchiglia. 2023. Lexical diversity in kinship across languages and dialects. Frontiers in Psychology 14 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference. 2798\u20132807","author":"Khishigsuren Temuulen","year":"2022","unstructured":"Temuulen Khishigsuren, G\u00e1bor Bella, Khuyagbaatar Batsuren, Abed\u00a0Alhakim Freihat, Nandu\u00a0Chandran Nair, Amarsanaa Ganbold, Hadi Khalilia, Yamini Chandrashekar, and Fausto Giunchiglia. 2022. Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. 2798\u20132807."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0077056"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.44"},{"key":"e_1_3_2_1_39_1","unstructured":"Yang Liu Yuanshun Yao Jean-Francois Ton Xiaoying Zhang Ruocheng Guo Hao Cheng Yegor Klochkov Muhammad\u00a0Faaiz Taufiq and Hang Li. 2023. Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models\u2019 Alignment. In Socially Responsible Language Modelling Research."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1491"},{"key":"e_1_3_2_1_41_1","volume-title":"WordNet: An electronic lexical database","author":"Miller A","unstructured":"George\u00a0A Miller. 1998. WordNet: An electronic lexical database. MIT press."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.2307\/3772751"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 48th annual meeting of the association for computational linguistics. 216\u2013225","author":"Navigli Roberto","year":"2010","unstructured":"Roberto Navigli and Simone\u00a0Paolo Ponzetto. 2010. BabelNet: Building a very large multilingual semantic network. In Proceedings of the 48th annual meeting of the association for computational linguistics. 216\u2013225."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.195"},{"key":"e_1_3_2_1_45_1","volume-title":"Digital Democracy","author":"Nyabola Nanjala","unstructured":"Nanjala Nyabola. 2018. Digital Democracy, Analogue Politics: How the Internet Era is Transforming Politics in Kenya. Zed Books, London."},{"key":"e_1_3_2_1_46_1","unstructured":"Oxford Internet Study. 2015. The Digital Language Divide. http:\/\/labs.theguardian.com\/digital-language-divide\/."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1356"},{"key":"e_1_3_2_1_48_1","volume-title":"International Journal sponsored by the Foundation\u201cFoundations of Language","author":"Rijkhoff Jan","year":"1993","unstructured":"Jan Rijkhoff, Dik Bakker, Kees Hengeveld, and Peter Kahrel. 1993. A method of language sampling. Studies in Language. International Journal sponsored by the Foundation\u201cFoundations of Language\u201d 17, 1 (1993), 169\u2013203."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.243"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.82"},{"key":"e_1_3_2_1_51_1","unstructured":"NLLB Team Marta\u00a0R. Costa-juss\u00e0 James Cross Onur\u00c7elebi Maha Elbayad Kenneth Heafield Kevin Heffernan Elahe Kalbassi Janice Lam Daniel Licht Jean Maillard Anna Sun Skyler Wang Guillaume Wenzek Al Youngblood Bapi Akula Loic Barrault Gabriel\u00a0Mejia Gonzalez Prangthip Hansanti John Hoffman Semarley Jarrett Kaushik\u00a0Ram Sadagopan Dirk Rowe Shannon Spruit Chau Tran Pierre Andrews Necip\u00a0Fazil Ayan Shruti Bhosale Sergey Edunov Angela Fan Cynthia Gao Vedanuj Goswami Francisco Guzm\u00e1n Philipp Koehn Alexandre Mourachko Christophe Ropers Safiyyah Saleem Holger Schwenk and Jeff Wang. 2022. No Language Left Behind: Scaling Human-Centered Machine Translation. arxiv:2207.04672\u00a0[cs.CL]"},{"key":"e_1_3_2_1_52_1","volume-title":"The Convention on the Protection and Promotion of the Diversity of Cultural Expressions. https:\/\/en.unesco.org\/creativity\/convention","author":"UNESCO.","year":"2005","unstructured":"UNESCO. 2005. The Convention on the Protection and Promotion of the Diversity of Cultural Expressions. https:\/\/en.unesco.org\/creativity\/convention (2005)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.188"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1017\/S000397561200015X"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.38"},{"key":"e_1_3_2_1_56_1","volume-title":"Justice and the Politics of Difference","author":"Young Iris\u00a0Marion","unstructured":"Iris\u00a0Marion Young. 1990. Justice and the Politics of Difference. Princeton University Press. Google-Books-ID: Q6keKguPrsAC."},{"key":"e_1_3_2_1_57_1","volume-title":"Zimmerman and Ben Bradley","author":"J.","year":"2019","unstructured":"Michael\u00a0J. Zimmerman and Ben Bradley. 2019. Intrinsic vs. Extrinsic Value. In The Stanford Encyclopedia of Philosophy (Spring 2019 ed.), Edward\u00a0N. Zalta (Ed.). Metaphysics Research Lab, Stanford University."}],"event":{"name":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658925","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3658925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:33:16Z","timestamp":1755883996000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":57,"alternative-id":["10.1145\/3630106.3658925","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3658925","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}