{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:11:51Z","timestamp":1784178711977,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":56,"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\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657955","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2368-2373","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Distillation for Multilingual Information Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"first","affiliation":[{"name":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-7086","authenticated-orcid":false,"given":"Dawn","family":"Lawrie","sequence":"additional","affiliation":[{"name":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3866-3013","authenticated-orcid":false,"given":"James","family":"Mayfield","sequence":"additional","affiliation":[{"name":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"}],"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\/2021.emnlp-main.79"},{"key":"e_1_3_2_1_2_1","volume-title":"CLEF 2000 -- Overview of Results. In Cross-Language Information Retrieval and Evaluation, Carol Peters (Ed.). Springer Berlin Heidelberg","author":"Braschler Martin","year":"2001","unstructured":"Martin Braschler. 2001 a. CLEF 2000 -- Overview of Results. In Cross-Language Information Retrieval and Evaluation, Carol Peters (Ed.). Springer Berlin Heidelberg, Berlin, Heidelberg, 89--101."},{"key":"e_1_3_2_1_3_1","volume-title":"CLEF 2001-Overview of Results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 9--26","author":"Braschler Martin","year":"2001","unstructured":"Martin Braschler. 2001 b. CLEF 2001-Overview of Results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 9--26."},{"key":"e_1_3_2_1_4_1","volume-title":"CLEF 2002-Overview of results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 9--27","author":"Braschler Martin","year":"2002","unstructured":"Martin Braschler. 2002. CLEF 2002-Overview of results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 9--27."},{"key":"e_1_3_2_1_5_1","volume-title":"CLEF 2003--Overview of results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 44--63","author":"Braschler Martin","year":"2003","unstructured":"Martin Braschler. 2003. CLEF 2003--Overview of results. In Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 44--63."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860497"},{"key":"e_1_3_2_1_10_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. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 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). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). Association for Machine Translation in the Americas, Virtual, 110--115","author":"Domhan Tobias","year":"2020","unstructured":"Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, and Kenneth Heafield. 2020. The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020. In Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). Association for Machine Translation in the Americas, Virtual, 110--115."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_14_1","volume-title":"Multilingual information management: Information, technology and translators","author":"Granell Ximo","unstructured":"Ximo Granell. 2014. Multilingual information management: Information, technology and translators. Chandos Publishing."},{"key":"e_1_3_2_1_15_1","volume-title":"EAMT","author":"Hieber Felix","year":"2020","unstructured":"Felix Hieber, Tobias Domhan, Michael Denkowski, and David Vilar. 2020. SOCKEYE 2: A Toolkit for Neural Machine Translation. In EAMT 2020. https:\/\/www.amazon.science\/publications\/sockeye-2-a-toolkit-for-neural-machine-translation"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113--122","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently teaching an effective dense retriever with balanced topic aware sampling. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113--122."},{"key":"e_1_3_2_1_17_1","volume-title":"Soft Prompt Decoding for Multilingual Dense Retrieval. arXiv preprint arXiv:2305.09025","author":"Huang Zhiqi","year":"2023","unstructured":"Zhiqi Huang, Hansi Zeng, Hamed Zamani, and James Allan. 2023. Soft Prompt Decoding for Multilingual Dense Retrieval. arXiv preprint arXiv:2305.09025 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/243199.243212"},{"key":"e_1_3_2_1_19_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence, Vol. 33, 1 (2010), 117--128."},{"key":"e_1_3_2_1_20_1","volume-title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval. arXiv preprint arXiv:2303.16145","author":"Jeronymo Vitor","year":"2023","unstructured":"Vitor Jeronymo, Roberto Lotufo, and Rodrigo Nogueira. 2023. NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval. arXiv preprint arXiv:2303.16145 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_22_1","volume-title":"Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oug uz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120103322711587"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/1948550617697177"},{"key":"e_1_3_2_1_26_1","volume-title":"Overview of the TREC 2022 NeuCLIR Track. In The Thirty-first Text REtrieval Conference (TREC 2022) Proceedings.","author":"Lawrie Dawn","year":"2022","unstructured":"Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, Luca Soldanini, and Eugene Yang. 2022a. Overview of the TREC 2022 NeuCLIR Track. In The Thirty-first Text REtrieval Conference (TREC 2022) Proceedings."},{"key":"e_1_3_2_1_27_1","volume-title":"Overview of the TREC 2023 NeuCLIR Track. In The Thirty-second Text REtrieval Conference (TREC 2023) Proceedings.","author":"Lawrie Dawn","year":"2023","unstructured":"Dawn Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, Luca Soldanini, and Eugene Yang. 2023 a. Overview of the TREC 2023 NeuCLIR Track. In The Thirty-second Text REtrieval Conference (TREC 2023) Proceedings."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_24"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28244-7_33"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591977"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.663"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.329"},{"key":"e_1_3_2_1_33_1","volume-title":"Jones","author":"Magdy Walid","year":"2011","unstructured":"Walid Magdy and Gareth J.F. Jones. 2011. Should MT systems be used as black boxes in CLIR?. In European Conference on Information Retrieval. Springer, 683--686."},{"key":"e_1_3_2_1_34_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 4 (2018), 824--836."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564406"},{"key":"e_1_3_2_1_36_1","unstructured":"Teruko Mitamura Eric Nyberg Hideki Shima Tsuneaki Kato Tatsunori Mori Chin-Yew Lin Ruihua Song Chuan-Jie Lin Tetsuya Sakai Donghong Ji et al. 2008. Overview of the NTCIR-7 ACLIA Tasks: Advanced Cross-Lingual Information Access.. In NTCIR."},{"key":"e_1_3_2_1_37_1","volume-title":"Oard","author":"Nair Suraj","year":"2022","unstructured":"Suraj Nair, Eugene Yang, Dawn Lawrie, Kevin Duh, Paul McNamee, Kenton Murray, James Mayfield, and Douglas W. Oard. 2022. Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models. In Advances in Information Retrieval: 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, April 10--14, 2022, Proceedings, Part I (Stavanger, Norway). Springer-Verlag, Berlin, Heidelberg, 382--396."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Nair Suraj","unstructured":"Suraj Nair, Eugene Yang, Dawn Lawrie, James Mayfield, and Douglas W. Oard. 2023. BLADE: Combining Vocabulary Pruning and Intermediate Pretraining for Scaleable Neural CLIR. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (Taipei, Taiwan) (SIGIR '23). Association for Computing Machinery, New York, NY, USA, 1219--1229."},{"key":"e_1_3_2_1_39_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv preprint arXiv:1611.09268","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv preprint arXiv:1611.09268 (2016). showeprint[arXiv]1611.09268 http:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_41_1","unstructured":"Carol Peters and Martin Braschler. 2002. The Importance of Evaluation for Cross-Language System Development: the CLEF Experience.. In LREC."},{"key":"e_1_3_2_1_42_1","volume-title":"Multilingual information retrieval: From research to practice","author":"Peters Carol","unstructured":"Carol Peters, Martin Braschler, and Paul Clough. 2012. Multilingual information retrieval: From research to practice. Springer."},{"key":"e_1_3_2_1_43_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2021","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2021. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 5835--5847."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-015-9255-1"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Reimers Nils","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01068419"},{"key":"e_1_3_2_1_48_1","volume-title":"Cross-lingual relevance transfer for document retrieval. arXiv preprint arXiv:1911.02989","author":"Shi P","year":"2019","unstructured":"P Shi and J Lin. 2019. Cross-lingual relevance transfer for document retrieval. arXiv preprint arXiv:1911.02989 (2019)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-007-9036-6"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390370"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.3115\/1117794.1117806"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_4"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531886"},{"key":"e_1_3_2_1_55_1","volume-title":"2024 b. Efficiency-Effectiveness Tradeoff of Probabilistic Structured Queries for Cross-Language Information Retrieval. arXiv preprint arXiv:2404.18797","author":"Yang Eugene","year":"2024","unstructured":"Eugene Yang, Suraj Nair, Dawn Lawrie, James Mayfield, Douglas W Oard, and Kevin Duh. 2024 b. Efficiency-Effectiveness Tradeoff of Probabilistic Structured Queries for Cross-Language Information Retrieval. arXiv preprint arXiv:2404.18797 (2024). https:\/\/arxiv.org\/abs\/2404.18797"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.12"}],"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\/3626772.3657955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:41:05Z","timestamp":1755841265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":56,"alternative-id":["10.1145\/3626772.3657955","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657955","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"}}]}}