{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T01:42:13Z","timestamp":1778463733749,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2024,12,8]]},"DOI":"10.1145\/3673791.3698412","type":"proceedings-article","created":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T06:24:16Z","timestamp":1733639056000},"page":"209-215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Simple Transformers: Open-source for All"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5482-664X","authenticated-orcid":false,"given":"Thilina C.","family":"Rajapakse","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-880X","authenticated-orcid":false,"given":"Andrew","family":"Yates","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.2996587"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/qje\/qjw024"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24027-5_20"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1160"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-03266-1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-01714--4"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01321-6"},{"key":"e_1_3_2_1_8_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arxiv:2401.08281 [cs.LG]"},{"key":"e_1_3_2_1_9_1","volume-title":"Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. ArXiv","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao, Xueguang Ma, Jimmy J. Lin, and Jamie Callan. 2022. Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. ArXiv, Vol. abs\/2203.05765 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Lucene in Action","author":"Gospodnetic Otis","unstructured":"Otis Gospodnetic and Erik Hatcher. 2004. Lucene in Action. Manning Publications."},{"key":"e_1_3_2_1_11_1","volume-title":"Accelerate: Training and Inference at Scale Made Simple, Efficient and Adaptable. https:\/\/github.com\/huggingface\/accelerate.","author":"Gugger Sylvain","year":"2022","unstructured":"Sylvain Gugger, Lysandre Debut, Thomas Wolf, Philipp Schmid, Zachary Mueller, Sourab Mangrulkar, Marc Sun, and Benjamin Bossan. 2022. Accelerate: Training and Inference at Scale Made Simple, Efficient and Adaptable. https:\/\/github.com\/huggingface\/accelerate."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1070.0748"},{"key":"e_1_3_2_1_13_1","volume-title":"Parameter-efficient Transfer Learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient Transfer Learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_15_1","volume-title":"Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551","author":"Joshi Mandar","year":"2017","unstructured":"Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551 (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_18_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Quentin Lhoest Albert Villanova del Moral Yacine Jernite Abhishek Thakur Patrick von Platen Suraj Patil Julien Chaumond Mariama Drame Julien Plu Lewis Tunstall Joe Davison Mario \u0160a\u0161ko Gunjan Chhablani Bhavitvya Malik Simon Brandeis Teven Le Scao Victor Sanh Canwen Xu Nicolas Patry Angelina McMillan-Major Philipp Schmid Sylvain Gugger Cl\u00e9ment Delangue Th\u00e9o Matussi\u00e8re Lysandre Debut Stas Bekman Pierric Cistac Thibault Goehringer Victor Mustar Fran\u00e7ois Lagunas Alexander Rush and Thomas Wolf. 2021. Datasets: A Community Library for Natural Language Processing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics Online and Punta Cana Dominican Republic 175--184. arxiv: 2109.02846 [cs.CL] https:\/\/aclanthology.org\/2021.emnlp-demo.21","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_21_1","volume-title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452","author":"Lin Sheng-Chieh","year":"2023","unstructured":"Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft.","author":"Mangrulkar Sourab","year":"2022","unstructured":"Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_2_1_23_1","unstructured":"Mariana Mazzucato. 2021. Mission Economy. Penguin Random House."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28241-6_7"},{"key":"e_1_3_2_1_25_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_26_1","volume-title":"Document Ranking with a Pretrained Sequence-to-Sequence Model. CoRR","author":"Nogueira Rodrigo Frassetto","year":"2020","unstructured":"Rodrigo Frassetto Nogueira, Zhiying Jiang, and Jimmy Lin. 2020. Document Ranking with a Pretrained Sequence-to-Sequence Model. CoRR, Vol. abs\/2003.06713 (2020). showeprint[arXiv]2003.06713 https:\/\/arxiv.org\/abs\/2003.06713"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Information Retrieval","author":"Ounis Iadh","unstructured":"Iadh Ounis, Gianni Amati, Vassilis Plachouras, Ben He, Craig Macdonald, and Douglas Johnson. 2005. Terrier Information Retrieval Platform. In Advances in Information Retrieval. Springer, 517--519."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.2196\/41205"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_30_1","volume-title":"In-context Retrieval-augmented Language Models. arXiv preprint arXiv:2302.00083","author":"Ram Ori","year":"2023","unstructured":"Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context Retrieval-augmented Language Models. arXiv preprint arXiv:2302.00083 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/aaai.12040"},{"key":"e_1_3_2_1_33_1","volume-title":"Franccois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilic, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Franccois Yvon, Matthias Gall\u00e9, et al. 2022. Bloom: A 176b-Parameter Open-access Multilingual Language Model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"Twin-Win Research","author":"Shneiderman Ben","unstructured":"Ben Shneiderman. 2018. Twin-Win Research. Springer."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Ben Shneiderman. 2022. Human-Centered AI. Oxford University Press.","DOI":"10.1093\/oso\/9780192845290.001.0001"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00540-0"},{"key":"e_1_3_2_1_37_1","unstructured":"Divya Siddarth Daron Acemoglu Danielle Allen Kate Crawford James Evans Michael Jordan and E. Glen Weyl. 2021. How AI Fails Us. Technical Report. Justic Health and Democracy Impact Initiative & Carr Cenetr for Human Rights Policy."},{"key":"e_1_3_2_1_38_1","volume-title":"The Digital Republic: On Freedom and Democracy in the 21st Century. Bloomsbury","author":"Susskind Jamie","unstructured":"Jamie Susskind. 2022. The Digital Republic: On Freedom and Democracy in the 21st Century. Bloomsbury."},{"key":"e_1_3_2_1_39_1","volume-title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_40_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_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08438-8"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. https:\/\/doi.org\/10.48550\/ARXIV.1706.03762","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_44_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Document Matching. CoRR","author":"Yang Liu","year":"2020","unstructured":"Liu Yang, Mingyang Zhang, Cheng Li, Michael Bendersky, and Marc Najork. 2020. Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Document Matching. CoRR, Vol. abs\/2004.12297 (2020). showeprint[arXiv]2004.12297 https:\/\/arxiv.org\/abs\/2004.12297"}],"event":{"name":"SIGIR-AP 2024: Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Tokyo Japan","acronym":"SIGIR-AP 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673791.3698412","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673791.3698412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:22:25Z","timestamp":1755879745000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673791.3698412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":45,"alternative-id":["10.1145\/3673791.3698412","10.1145\/3673791"],"URL":"https:\/\/doi.org\/10.1145\/3673791.3698412","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"2024-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}