{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:43:05Z","timestamp":1785249785012,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657867","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"553-563","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7248-7503","authenticated-orcid":false,"given":"Andreea","family":"Iana","sequence":"first","affiliation":[{"name":"University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1301-6314","authenticated-orcid":false,"given":"Goran","family":"Glava\u0161","sequence":"additional","affiliation":[{"name":"University of W\u00fcrzburg, W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4386-8195","authenticated-orcid":false,"given":"Heiko","family":"Paulheim","sequence":"additional","affiliation":[{"name":"University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1033"},{"key":"e_1_3_2_1_2_1","volume-title":"Neural machine translation by jointly learning to align and translate. ICLR","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. ICLR (2014)."},{"key":"e_1_3_2_1_3_1","volume-title":"Free speech in the algorithmic society: Big data, private governance, and new school speech regulation. UCDL rev","author":"Balkin Jack M","year":"2017","unstructured":"Jack M Balkin. 2017. Free speech in the algorithmic society: Big data, private governance, and new school speech regulation. UCDL rev., Vol. 51 (2017), 1149."},{"key":"e_1_3_2_1_4_1","volume-title":"The Gradient","volume":"14","author":"Bender Emily","year":"2019","unstructured":"Emily Bender. 2019. The# benderrule: On naming the languages we study and why it matters. The Gradient, Vol. 14 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of KDD cup and workshop","volume":"2007","author":"Bennett James","year":"2007","unstructured":"James Bennett, Stan Lanning, et al. 2007. The netflix prize. In Proceedings of KDD cup and workshop, Vol. 2007. New York, 35."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2. 2787--2795","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Dur\u00e1n, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2. 2787--2795. https:\/\/dl.acm.org\/doi\/abs\/10.5555\/2999792.2999923"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 7059--7069","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau and Guillaume Lample. 2019. Cross-lingual language model pretraining. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 7059--7069."},{"key":"e_1_3_2_1_10_1","volume-title":"Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, et al.","author":"Marta R","year":"2022","unstructured":"Marta R Costa-juss\u00e0, James Cross, Onur cCelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, et al. 2022. No language left behind: Scaling human-centered machine translation. arXiv preprint arXiv:2207.04672 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406095"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.252"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3270323.3270328"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7385533"},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan Angela","year":"2021","unstructured":"Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, et al. 2021. Beyond english-centric multilingual machine translation. Journal of Machine Learning Research, Vol. 22, 107 (2021), 1--48.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2954957"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106426.3109436"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583383"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00446"},{"key":"e_1_3_2_1_20_1","unstructured":"Harald Hammarstr\u00f6m Robert Forkel Martin Haspelmath and Sebastian Bank. 2021. glottolog\/glottolog: Glottolog database 4.4."},{"key":"e_1_3_2_1_21_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis)","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), Vol. 5, 4 (2015), 1--19."},{"key":"e_1_3_2_1_22_1","volume-title":"Algorithms, Automation, and News","author":"Helberger Natali","unstructured":"Natali Helberger. 2021. On the democratic role of news recommenders. In Algorithms, Automation, and News. Routledge, 14--33."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Workshop on News Recommendation and Analytics co-located with RecSys","author":"Iana Andreea","year":"2023","unstructured":"Andreea Iana, Mehwish Alam, Alexander Grote, Katharina Luwig, Philipp M\u00fcller, Christof Weinhardt, and Heiko Paulheim. 2023. NeMig-A Bilingual News Collection and Knowledge Graph about Migration. In Proceedings of the Workshop on News Recommendation and Analytics co-located with RecSys 2023."},{"key":"e_1_3_2_1_24_1","unstructured":"Andreea Iana Mehwish Alam and Heiko Paulheim. [n. d.]. A survey on knowledge-aware news recommender systems. Semantic Web Preprint ( [n. d.]) 1--62."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.26"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592062"},{"key":"e_1_3_2_1_27_1","volume-title":"2023 d. Train once, use flexibly: A modular framework for multi-aspect neural news recommendation. arXiv preprint arXiv:2307.16089","author":"Iana Andreea","year":"2023","unstructured":"Andreea Iana, Goran Glavavs, and Heiko Paulheim. 2023 d. Train once, use flexibly: A modular framework for multi-aspect neural news recommendation. arXiv preprint arXiv:2307.16089 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1047"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.560"},{"key":"e_1_3_2_1_30_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2516641.2516643"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_33_1","volume-title":"Adam: A method for stochastic optimization. ICLR","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. ICLR (2014)."},{"key":"e_1_3_2_1_34_1","volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","unstructured":"Klaus Krippendorff. 2013. Content analysis: An introduction to its methodology. Sage publications."},{"key":"e_1_3_2_1_35_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Kudugunta Sneha","year":"2023","unstructured":"Sneha Kudugunta, Isaac Rayburn Caswell, Biao Zhang, Xavier Garcia, Derrick Xin, Aditya Kusupati, Romi Stella, Ankur Bapna, and Orhan Firat. 2023. MADLAD-400: A Multilingual And Document-Level Large Audited Dataset. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.363"},{"key":"e_1_3_2_1_37_1","volume-title":"Ethnologue: languages of the world","author":"Lewis M Paul","year":"2009","unstructured":"M Paul Lewis, Gary F Simons, and Charles D Fennig. 2009. Ethnologue: languages of the world, Dallas, Texas: SIL International. Online version: http:\/\/www. ethnologue. com, Vol. 12, 12 (2009), 2010."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.29"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944927"},{"key":"e_1_3_2_1_40_1","volume-title":"PBNR: Prompt-based News Recommender System. arXiv preprint arXiv:2304.07862","author":"Li Xinyi","year":"2023","unstructured":"Xinyi Li, Yongfeng Zhang, and Edward C Malthouse. 2023. PBNR: Prompt-based News Recommender System. arXiv preprint arXiv:2304.07862 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2019.1662636"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2002"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412237"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the The First Workshop on the Normative Design and Evaluation of Recommender Systems (NORMalize 2023), co-located with the ACM Conference on Recommender Systems 2023 (RecSys","author":"Lucas Joel Pinho","year":"2023","unstructured":"Joel Pinho Lucas, Jo\u00e3o Felipe Guedes da Silva, and Let\u00edcia Freire Figueiredo. 2023. NPR: a News Portal Recommendations dataset. In Proceedings of the The First Workshop on the Normative Design and Evaluation of Recommender Systems (NORMalize 2023), co-located with the ACM Conference on Recommender Systems 2023 (RecSys 2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"The filter bubble: What the Internet is hiding from you","author":"Pariser Eli","unstructured":"Eli Pariser. 2011. The filter bubble: What the Internet is hiding from you. Penguin UK."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-demos.33"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.185"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Matt Post. 2018. A Call for Clarity in Reporting BLEU Scores. In Proceedings of the Third Conference on Machine Translation: Research Papers Ondvrej Bojar Rajen Chatterjee Christian Federmann Mark Fishel Yvette Graham Barry Haddow Matthias Huck Antonio Jimeno Yepes Philipp Koehn Christof Monz Matteo Negri Aur\u00e9lie N\u00e9v\u00e9ol Mariana Neves Matt Post Lucia Specia Marco Turchi and Karin Verspoor (Eds.). Association for Computational Linguistics Brussels Belgium 186--191. https:\/\/doi.org\/10.18653\/v1\/W18-6319","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462861"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.424"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531790"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531778"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.128"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.423"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.736"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.02627"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)","author":"Tiedemann J\u00f6rg","year":"2012","unstructured":"J\u00f6rg Tiedemann. 2012. Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12) (23--25), Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Mehmet Ugur Dogan, Bente Maegaard, Joseph Mariani, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association (ELRA), Istanbul, Turkey."},{"key":"e_1_3_2_1_58_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000--6010","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000--6010. https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186175"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747149"},{"key":"e_1_3_2_1_62_1","volume-title":"Polylm: An open source polyglot large language model. arXiv preprint arXiv:2307.06018","author":"Wei Xiangpeng","year":"2023","unstructured":"Xiangpeng Wei, Haoran Wei, Huan Lin, Tianhao Li, Pei Zhang, Xingzhang Ren, Mei Li, Yu Wan, Zhiwei Cao, Binbin Xie, et al. 2023. Polylm: An open source polyglot large language model. arXiv preprint arXiv:2307.06018 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"On Learning Universal Representations Across Languages. In International Conference on Learning Representations.","author":"Wei Xiangpeng","year":"2020","unstructured":"Xiangpeng Wei, Rongxiang Weng, Yue Hu, Luxi Xing, Heng Yu, and Weihua Luo. 2020. On Learning Universal Representations Across Languages. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_64_1","volume-title":"Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al. 2022","year":"2022","unstructured":"BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/536"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330665"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1110"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1671"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/348"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3530257"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.6"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463069"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.00539"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-022-01473-1"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_1_76_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.368"},{"key":"e_1_3_2_1_79_1","volume-title":"Prompt learning for news recommendation. arXiv preprint arXiv:2304.05263","author":"Zhang Zizhuo","year":"2023","unstructured":"Zizhuo Zhang and Bang Wang. 2023. Prompt learning for news recommendation. arXiv preprint arXiv:2304.05263 (2023)."},{"key":"e_1_3_2_1_80_1","unstructured":"Ethan Zuckerman. 2008. The polyglot internet. (2008). https:\/\/ethanzuckerman.com\/the-polyglot-internet\/"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657867","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:31:00Z","timestamp":1755840660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":80,"alternative-id":["10.1145\/3626772.3657867","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657867","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}