{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:11:50Z","timestamp":1784178710871,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031560590","type":"print"},{"value":"9783031560606","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-56060-6_4","type":"book-chapter","created":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T15:02:17Z","timestamp":1710514937000},"page":"50-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Translate-Distill: Learning Cross-Language Dense Retrieval by\u00a0Translation and\u00a0Distillation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-7086","authenticated-orcid":false,"given":"Dawn","family":"Lawrie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3866-3013","authenticated-orcid":false,"given":"James","family":"Mayfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1696-0407","authenticated-orcid":false,"given":"Douglas W.","family":"Oard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3345-6346","authenticated-orcid":false,"given":"Scott","family":"Miller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,16]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","unstructured":"Asai, A., Kasai, J., Clark, J., Lee, K., Choi, E., Hajishirzi, H.: XOR QA: cross-lingual open-retrieval question answering. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 547\u2013564, Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.46","DOI":"10.18653\/v1\/2021.naacl-main.46"},{"key":"4_CR2","unstructured":"Bonifacio, L., et al.: mMARCO: A multilingual version of the MS MARCO passage ranking dataset (2021). arXiv preprint arXiv:2108.13897"},{"key":"4_CR3","doi-asserted-by":"publisher","unstructured":"Chi, Z., et al.: Improving pretrained cross-lingual language models via self-labeled word alignment. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3418\u20133430, Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.265","DOI":"10.18653\/v1\/2021.acl-long.265"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451, Association for Computational Linguistics, Online (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Costello, C., Yang, E., Lawrie, D., Mayfield, J.: Patapsco: a python framework for cross-language information retrieval experiments. In: Proceedings of the 44th European Conference on Information Retrieval (ECIR) (2022)","DOI":"10.1007\/978-3-030-99739-7_33"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Dai, Z., Callan, J.: Deeper text understanding for IR with contextual neural language modeling. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 985\u2013988 (2019)","DOI":"10.1145\/3331184.3331303"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Darwish, K., Oard, D.W.: Probabilistic structured query methods. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 338\u2013344 (2003)","DOI":"10.1145\/860435.860497"},{"key":"4_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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), pp. 4171\u20134186, Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: From distillation to hard negative sampling: Making sparse neural IR models more effective. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2353\u20132359 (2022)","DOI":"10.1145\/3477495.3531857"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: sparse lexical and expansion model for first stage ranking. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2288\u20132292 (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2843\u20132853, Association for Computational Linguistics, Dublin, Ireland (2022)","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Jeronymo, V., Lotufo, R., Nogueira, R.: NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large boring rerankers for cross-lingual retrieval. arXiv preprint arXiv:2303.16145 (2023)","DOI":"10.6028\/NIST.SP.500-338.neuclir-NM.unicamp"},{"key":"4_CR13","unstructured":"Jiao, W., Wang, W., Huang, J., Wang, X., Tu, Z.: Is ChatGPT a good translator? Yes with GPT-4 as the engine (2023). arXiv preprint arXiv:2301.08745"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering (2020). arXiv preprint arXiv:2004.04906","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pp. 39\u201348 (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"4_CR17","unstructured":"Landauer, T.K., Littman, M.L.: A statistical method for language-independent representation of the topical content of text segments. In: Proceedings of the Eleventh International Conference: Expert Systems and Their Applications, vol. 8, p. 85, Citeseer (1991)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Lawrie, D., et al.: Overview of the TREC 2022 NeuCLIR track (2023)","DOI":"10.6028\/NIST.SP.500-338.neuclir-overview"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Lawrie, D., Mayfield, J., Oard, D.W., Yang, E., Nair, S., Galu\u0161\u010d\u00e1kov\u00e1, P.: HC3: A suite of test collections for CLIR evaluation over informal text. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (Taipei, Taiwan) (SIGIR 2023). (2023)","DOI":"10.1145\/3539618.3591893"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Franz, M., Sultan, M.A., Iyer, B., Lee, Y.S., Sil, A.: Learning cross-lingual IR from an English retriever. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4428\u20134436 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.329"},{"key":"4_CR21","doi-asserted-by":"publisher","unstructured":"Lin, J., Nogueira, R., Yates, A.: Pretrained transformers for text ranking: BERT and beyond. Springer Nature (2022). https:\/\/doi.org\/10.1007\/978-3-031-02181-7","DOI":"10.1007\/978-3-031-02181-7"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: PROD: progressive distillation for dense retrieval. In: Proceedings of the ACM Web Conference 2023, pp. 3299\u20133308 (2023)","DOI":"10.1145\/3543507.3583421"},{"key":"4_CR23","unstructured":"Liu, Y., et al.: RoBERTa: A robustly optimized BERT pretraining approach (2019)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"MacAvaney, S., Yates, A., Feldman, S., Downey, D., Cohan, A., Goharian, N.: Simplified data wrangling with IR_datasets. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2429\u20132436 (2021)","DOI":"10.1145\/3404835.3463254"},{"key":"4_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-030-99736-6_26","volume-title":"Advances in Information Retrieval","author":"S Nair","year":"2022","unstructured":"Nair, S., et al.: Transfer learning approaches for building cross-language dense retrieval models. In: Hagen, M., et al. (eds.) ECIR 2022. LNCS, vol. 13185, pp. 382\u2013396. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-99736-6_26"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Nair, S., Yang, E., Lawrie, D., Mayfield, J., Oard, D.W.: 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, pp. 1219\u20131229, SIGIR 2023, Association for Computing Machinery, New York, NY, USA (2023). ISBN 9781450394086","DOI":"10.1145\/3539618.3591644"},{"key":"4_CR27","unstructured":"Nguyen, T., et al.: MS MARCO: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016). http:\/\/arxiv.org\/abs\/1611.09268"},{"key":"4_CR28","doi-asserted-by":"publisher","unstructured":"Nogueira, R., Jiang, Z., Pradeep, R., Lin, J.: Document ranking with a pretrained sequence-to-sequence model. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 708\u2013718, Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.63","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"4_CR29","unstructured":"Nogueira, R., Yang, W., Cho, K., Lin, J.: Multi-stage document ranking with BERT (2019). arXiv preprint arXiv:1910.14424"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Pirkola, A.: The effects of query structure and dictionary setups in dictionary-based cross-language information retrieval. In: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 55\u201363 (1998)","DOI":"10.1145\/290941.290957"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Qu, Y., et al.: 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, pp. 5835\u20135847, Association for Computational Linguistics, Online (2021)","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"4_CR32","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Ruwase, O., Rasley, J., Smith, S., He, Y.: Zero-infinity: breaking the GPU memory wall for extreme scale deep learning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2021)","DOI":"10.1145\/3458817.3476205"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"4_CR35","unstructured":"Rehder, B., Littman, M.L.: Automatic 3-language cross-language information retrieval. In: Information Technology: The Sixth Text REtrieval Conference (TREC-6), vol. 500, p. 233, National Institute of Standards and Technology (1998)"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Potts, C., Zaharia, M.: PLAID: an efficient engine for late interaction retrieval. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1747\u20131756 (2022)","DOI":"10.1145\/3511808.3557325"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.: ColBERTv2: effective and efficient retrieval via lightweight late interaction. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3715\u20133734, Association for Computational Linguistics, Seattle, United States (Jul 2022)","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Sheridan, P., Ballerini, J.P.: Experiments in multilingual information retrieval using the SPIDER system. In: Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 58\u201365 (1996)","DOI":"10.1145\/243199.243213"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Sun, S., Duh, K.: CLIRMatrix: a massively large collection of bilingual and multilingual datasets for cross-lingual information retrieval. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4160\u20134170 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.340"},{"key":"4_CR40","doi-asserted-by":"publisher","unstructured":"Wang, J., Oard, D.W.: Matching meaning for cross-language information retrieval. Inf. Process. Manag. 48(4), 631\u2013653 (2012). ISSN 0306\u20134573, https:\/\/doi.org\/10.1016\/j.ipm.2011.09.003","DOI":"10.1016\/j.ipm.2011.09.003"},{"key":"4_CR41","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: MiniLM: deep self-attention distillation for task-agnostic compression of pre-trained transformers. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020, Curran Associates Inc., Red Hook, NY, USA (2020), ISBN 9781713829546"},{"key":"4_CR42","doi-asserted-by":"publisher","unstructured":"Yang, E., Nair, S., Chandradevan, R., Iglesias-Flores, R., Oard, D.W.: C3: continued pretraining with contrastive weak supervision for cross language ad-hoc retrieval. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2507\u20132512, SIGIR 2022, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3477495.3531886","DOI":"10.1145\/3477495.3531886"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Zeng, H., Zamani, H., Vinay, V.: Curriculum learning for dense retrieval distillation. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1979\u20131983 (2022)","DOI":"10.1145\/3477495.3531791"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56060-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T11:10:19Z","timestamp":1731582619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56060-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560590","9783031560606"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56060-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"578","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"110","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"69","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}