{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:49:06Z","timestamp":1785336546297,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","award":["2019-19051600007"],"award-info":[{"award-number":["2019-19051600007"]}],"id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011038","name":"Office of the Director of National Intelligence","doi-asserted-by":"publisher","award":["2019-19051600007"],"award-info":[{"award-number":["2019-19051600007"]}],"id":[{"id":"10.13039\/100011038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570468","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"1048-1056","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2939-1936","authenticated-orcid":false,"given":"Zhiqi","family":"Huang","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7913-8632","authenticated-orcid":false,"given":"Puxuan","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0132-5694","authenticated-orcid":false,"given":"James","family":"Allan","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings. arXiv preprint arXiv:2110.02887","author":"Alqahtani Sawsan","year":"2021","unstructured":"Sawsan Alqahtani, Garima Lalwani, Yi Zhang, Salvatore Romeo, and Saab Mansour. 2021. Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings. arXiv preprint arXiv:2110.02887 (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341981.3344236"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401035"},{"key":"e_1_3_2_1_4_1","volume-title":"mmarco: A multilingual version of the ms marco passage ranking dataset. arXiv preprint arXiv:2108.13897","author":"Bonifacio Luiz Henrique","year":"2021","unstructured":"Luiz Henrique Bonifacio, Israel Campiotti, Vitor Jeronymo, Roberto Lotufo, and Rodrigo Nogueira. 2021. mmarco: A multilingual version of the ms marco passage ranking dataset. arXiv preprint arXiv:2108.13897 (2021)."},{"key":"e_1_3_2_1_5_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_6_1","volume-title":"Improving sequence-to-sequence learning via optimal transport. arXiv preprint arXiv:1901.06283","author":"Chen Liqun","year":"2019","unstructured":"Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Haichao Zhang, Bai Li, Dinghan Shen, Changyou Chen, and Lawrence Carin. 2019. Improving sequence-to-sequence learning via optimal transport. arXiv preprint arXiv:1901.06283 (2019)."},{"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","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","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."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.480"},{"key":"e_1_3_2_1_11_1","article-title":"Optimal transport for domain adaptation","volume":"1","author":"Flamary R","year":"2016","unstructured":"R Flamary, N Courty, D Tuia, and A Rakotomamonjy. 2016. Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell, Vol. 1 (2016).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"e_1_3_2_1_14_1","unstructured":"Geoffrey Hinton Oriol Vinyals Jeff Dean et al. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 Vol. 2 7 (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666","author":"Sebastian","year":"2020","unstructured":"Sebastian Hofst\"atter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482452"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4020"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.329"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210157"},{"key":"e_1_3_2_1_22_1","volume-title":"SIGIR'19","author":"Litschko Robert","year":"2018","unstructured":"Robert Litschko, Goran Glavavs, Simone Paolo Ponzetto, and Ivan Vuli\u0107. 2018b. Unsupervised cross-lingual information retrieval using monolingual data only. In SIGIR'19. 1253--1256."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331324"},{"key":"e_1_3_2_1_24_1","volume-title":"Faculty Distillation with Optimal Transport. arXiv preprint arXiv:2204.11526","author":"Lu Su","year":"2022","unstructured":"Su Lu, Han-Jia Ye, and De-Chuan Zhan. 2022. Faculty Distillation with Optimal Transport. arXiv preprint arXiv:2204.11526 (2022)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining.","author":"Ma Rongrong","unstructured":"Rongrong Ma, Guansong Pang, Ling Chen, and Anton van den Hengel. 2022. Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_26"},{"key":"e_1_3_2_1_28_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPs.","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. In CoCo@ NIPs."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21359"},{"key":"e_1_3_2_1_30_1","volume-title":"Cosda-ml: Multi-lingual code-switching data augmentation for zero-shot cross-lingual nlp. arXiv preprint arXiv:2006.06402","author":"Qin Libo","year":"2020","unstructured":"Libo Qin, Minheng Ni, Yue Zhang, and Wanxiang Che. 2020. Cosda-ml: Multi-lingual code-switching data augmentation for zero-shot cross-lingual nlp. arXiv preprint arXiv:2006.06402 (2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"Making monolingual sentence embeddings multilingual using knowledge distillation. arXiv preprint arXiv:2004.09813","author":"Reimers Nils","year":"2020","unstructured":"Nils Reimers and Iryna Gurevych. 2020. Making monolingual sentence embeddings multilingual using knowledge distillation. arXiv preprint arXiv:2004.09813 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.613"},{"key":"e_1_3_2_1_33_1","volume-title":"Improving GANs using optimal transport. arXiv preprint arXiv:1803.05573","author":"Salimans Tim","year":"2018","unstructured":"Tim Salimans, Han Zhang, Alec Radford, and Dimitris Metaxas. 2018. Improving GANs using optimal transport. arXiv preprint arXiv:1803.05573 (2018)."},{"key":"e_1_3_2_1_34_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2073"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation","author":"Tiedemann J\u00f6rg","year":"2020","unstructured":"J\u00f6rg Tiedemann and Santhosh Thottingal. 2020. OPUS-MT -- Building open translation services for the World. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Lisboa, Portugal, 479--480."},{"key":"e_1_3_2_1_37_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval. 363--372","author":"Vuli\u0107 Ivan","year":"2015","unstructured":"Ivan Vuli\u0107 and Marie-Francine Moens. 2015. Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval. 363--372."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_40_1","volume-title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation. arXiv preprint arXiv:2112.09445","author":"Wu Bichen","year":"2021","unstructured":"Bichen Wu, Ruizhe Cheng, Peizhao Zhang, Peter Vajda, and Joseph E Gonzalez. 2021. Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation. arXiv preprint arXiv:2112.09445 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Are all languages created equal in multilingual BERT? arXiv preprint arXiv:2005.09093","author":"Wu Shijie","year":"2020","unstructured":"Shijie Wu and Mark Dredze. 2020. Are all languages created equal in multilingual BERT? arXiv preprint arXiv:2005.09093 (2020)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of The 35th Uncertainty in Artificial Intelligence Conference (Proceedings of Machine Learning Research","author":"Xie Yujia","year":"2020","unstructured":"Yujia Xie, Xiangfeng Wang, Ruijia Wang, and Hongyuan Zha. 2020b. A Fast Proximal Point Method for Computing Exact Wasserstein Distance. In Proceedings of The 35th Uncertainty in Artificial Intelligence Conference (Proceedings of Machine Learning Research, Vol. 115), Ryan P. Adams and Vibhav Gogate (Eds.). PMLR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401322"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449830"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951463"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6129"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570468","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570468","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":47,"alternative-id":["10.1145\/3539597.3570468","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570468","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}