{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:31:18Z","timestamp":1775953878730,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531863","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"2387-2392","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":82,"title":["InPars: Unsupervised Dataset Generation for Information Retrieval"],"prefix":"10.1145","author":[{"given":"Luiz","family":"Bonifacio","sequence":"first","affiliation":[{"name":"Zeta Alpha, NeuralMind, & University of Campinas, Amsterdam, Netherlands"}]},{"given":"Hugo","family":"Abonizio","sequence":"additional","affiliation":[{"name":"Zeta Alpha & NeuralMind, Amsterdam, Netherlands"}]},{"given":"Marzieh","family":"Fadaee","sequence":"additional","affiliation":[{"name":"Zeta Alpha, Amsterdam, Netherlands"}]},{"given":"Rodrigo","family":"Nogueira","sequence":"additional","affiliation":[{"name":"Zeta Alpha, NeuralMind, University of Campinas, & University of Waterloo, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6233"},{"key":"e_1_3_2_2_2_1","volume-title":"Language Models are Few-Shot Learners. CoRR abs\/2005.14165","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown , Benjamin Mann , Nick Ryder , Melanie Subbiah , Jared Kaplan , Prafulla Dhariwal , Arvind Neelakantan , Pranav Shyam , Girish Sastry , Amanda Askell , Sandhini Agarwal , Ariel Herbert-Voss , Gretchen Krueger , Tom Henighan , Rewon Child , Aditya Ramesh , Daniel M. Ziegler , Jeffrey Wu , Clemens Winter , Christopher Hesse , Mark Chen , Eric Sigler , Mateusz Litwin , Scott Gray , Benjamin Chess , Jack Clark , Christopher Berner , Sam McCandlish , Alec Radford , Ilya Sutskever , and Dario Amodei . 2020. Language Models are Few-Shot Learners. CoRR abs\/2005.14165 ( 2020 ). arXiv:2005.14165 https:\/\/arxiv.org\/abs\/2005.14165 Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. CoRR abs\/2005.14165 (2020). arXiv:2005.14165 https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080819"},{"key":"e_1_3_2_2_4_1","volume-title":"Overview of the TREC 2020 deep learning track. CoRR abs\/2102","author":"Craswell Nick","year":"2021","unstructured":"Nick Craswell , Bhaskar Mitra , Emine Yilmaz , and Daniel Campos . 2021 . Overview of the TREC 2020 deep learning track. CoRR abs\/2102 .07662 (2021). arXiv:2102.07662 https:\/\/arxiv.org\/abs\/2102.07662 Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. CoRR abs\/2102.07662 (2021). arXiv:2102.07662 https:\/\/arxiv.org\/abs\/2102.07662"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2090"},{"key":"e_1_3_2_2_7_1","volume-title":"Unsupervised corpus aware language model pre-training for dense passage retrieval. arXiv preprint arXiv:2108.05540","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan . 2021. Unsupervised corpus aware language model pre-training for dense passage retrieval. arXiv preprint arXiv:2108.05540 ( 2021 ). Luyu Gao and Jamie Callan. 2021. Unsupervised corpus aware language model pre-training for dense passage retrieval. arXiv preprint arXiv:2108.05540 (2021)."},{"key":"e_1_3_2_2_8_1","unstructured":"Jesse Michael Han Igor Babuschkin Harrison Edwards Arvind Neelakantan Tao Xu Stanislas Polu Alex Ray Pranav Shyam Aditya Ramesh Alec Radford etal 2021. Unsupervised Neural Machine Translation with Generative Language Models Only. arXiv preprint arXiv:2110.05448 (2021).  Jesse Michael Han Igor Babuschkin Harrison Edwards Arvind Neelakantan Tao Xu Stanislas Polu Alex Ray Pranav Shyam Aditya Ramesh Alec Radford et al. 2021. Unsupervised Neural Machine Translation with Generative Language Models Only. arXiv preprint arXiv:2110.05448 (2021)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080751"},{"key":"e_1_3_2_2_10_1","volume-title":"The Curious Case of Neural Text Degeneration. In International Conference on Learning Representations.","author":"Holtzman Ari","year":"2019","unstructured":"Ari Holtzman , Jan Buys , Li Du , Maxwell Forbes , and Yejin Choi . 2019 . The Curious Case of Neural Text Degeneration. In International Conference on Learning Representations. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The Curious Case of Neural Text Degeneration. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","volume-title":"Towards Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard , Mathilde Caron , Lucas Hosseini , Sebastian Riedel , Piotr Bojanowski , Armand Joulin , and Edouard Grave . 2021. Towards Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv preprint arXiv:2112.09118 ( 2021 ). Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Towards Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_13_1","volume-title":"Dense Passage Retrieval for Open-Domain Question Answering. CoRR abs\/2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin , Barlas Oguz , Sewon Min , Ledell Wu , Sergey Edunov , Danqi Chen , and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. CoRR abs\/2004.04906 ( 2020 ). arXiv:2004.04906 https:\/\/arxiv.org\/abs\/2004.04906 Vladimir Karpukhin, Barlas Oguz, Sewon Min, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. CoRR abs\/2004.04906 (2020). arXiv:2004.04906 https:\/\/arxiv.org\/abs\/2004.04906"},{"key":"e_1_3_2_2_14_1","volume-title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. CoRR abs\/2004.12832","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia . 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. CoRR abs\/2004.12832 ( 2020 ). arXiv:2004.12832 https:\/\/arxiv.org\/abs\/2004.12832 Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. CoRR abs\/2004.12832 (2020). arXiv:2004.12832 https:\/\/arxiv.org\/abs\/2004.12832"},{"key":"e_1_3_2_2_15_1","volume-title":"Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv preprint arXiv:1805.06201","author":"Kobayashi Sosuke","year":"2018","unstructured":"Sosuke Kobayashi . 2018. Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv preprint arXiv:1805.06201 ( 2018 ). Sosuke Kobayashi. 2018. Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv preprint arXiv:1805.06201 (2018)."},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems. 18--26","author":"Kumar Varun","year":"2020","unstructured":"Varun Kumar , Ashutosh Choudhary , and Eunah Cho . 2020 . Data Augmentation using Pre-trained Transformer Models . In Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems. 18--26 . Varun Kumar, Ashutosh Choudhary, and Eunah Cho. 2020. Data Augmentation using Pre-trained Transformer Models. In Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems. 18--26."},{"key":"e_1_3_2_2_17_1","volume-title":"Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski , Jennimaria Palomaki , Olivia Redfield , Michael Collins , Ankur Parikh , Chris Alberti , Danielle Epstein , Illia Polosukhin , Matthew Kelcey , Jacob Devlin , Kenton Lee , Kristina N. Toutanova , Llion Jones , Ming-Wei Chang , Andrew Dai , Jakob Uszkoreit , Quoc Le , and Slav Petrov . 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics ( 2019 ). Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics (2019)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_2_19_1","volume-title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation. arXiv:2201.05955 [cs.CL].","author":"Liu Alisa","year":"2022","unstructured":"Alisa Liu , Swabha Swayamdipta , Noah A. Smith , and Yejin Choi . 2022 . WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation. arXiv:2201.05955 [cs.CL]. Alisa Liu, Swabha Swayamdipta, Noah A. Smith, and Yejin Choi. 2022. WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation. arXiv:2201.05955 [cs.CL]."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098011"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.92"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 4171--4179","author":"MacAvaney Sean","year":"2020","unstructured":"Sean MacAvaney , Arman Cohan , and Nazli Goharian . 2020 . SLEDGE: a simple yet effective zero-shot baseline for coronavirus scientific knowledge search . In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 4171--4179 . Sean MacAvaney, Arman Cohan, and Nazli Goharian. 2020. SLEDGE: a simple yet effective zero-shot baseline for coronavirus scientific knowledge search. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 4171--4179."},{"key":"e_1_3_2_2_23_1","volume-title":"Companion Proceedings of the The Web Conference 2018 (Lyon, France) (WWW '18). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE","author":"Maia Macedo","year":"1941","unstructured":"Macedo Maia , Siegfried Handschuh , Andr\u00e9 Freitas , Brian Davis , Ross McDermott , Manel Zarrouk , and Alexandra Balahur . 2018. WWW'18 Open Challenge: Financial Opinion Mining and Question Answering . In Companion Proceedings of the The Web Conference 2018 (Lyon, France) (WWW '18). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE , 1941 --1942. https:\/\/doi.org\/10.1145\/3184558.3192301 10.1145\/3184558.3192301 Macedo Maia, Siegfried Handschuh, Andr\u00e9 Freitas, Brian Davis, Ross McDermott, Manel Zarrouk, and Alexandra Balahur. 2018. WWW'18 Open Challenge: Financial Opinion Mining and Question Answering. In Companion Proceedings of the The Web Conference 2018 (Lyon, France) (WWW '18). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 1941--1942. https:\/\/doi.org\/10.1145\/3184558.3192301"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148246"},{"key":"e_1_3_2_2_25_1","unstructured":"Yu Meng Jiaxin Huang Yu Zhang and Jiawei Han. 2022. Generating Training Data with Language Models: Towards Zero-Shot Language Understanding. arXiv:2202.04538 [cs.CL]  Yu Meng Jiaxin Huang Yu Zhang and Jiawei Han. 2022. Generating Training Data with Language Models: Towards Zero-Shot Language Understanding. arXiv:2202.04538 [cs.CL]"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.103"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463093"},{"key":"e_1_3_2_2_28_1","volume-title":"Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan , Tao Xu , Raul Puri , Alec Radford , Jesse Michael Han , Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022 . Text and Code Embeddings by Contrastive Pre-Training . arXiv preprint arXiv:2201.10005 (2022). Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022. Text and Code Embeddings by Contrastive Pre-Training. arXiv preprint arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_2_29_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. CoRR abs\/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. CoRR abs\/1611.09268 (2016). arXiv:1611.09268 http:\/\/arxiv.org\/abs\/1611.09268 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. CoRR abs\/1611.09268 (2016). arXiv:1611.09268 http:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_2_2_30_1","unstructured":"Jianmo Ni Chen Qu Jing Lu Zhuyun Dai Gustavo Hern\u00e1ndez \u00c1brego Ji Ma Vincent Y Zhao Yi Luan Keith B Hall Ming-Wei Chang etal 2021. Large Dual Encoders Are Generalizable Retrievers. arXiv preprint arXiv:2112.07899 (2021).  Jianmo Ni Chen Qu Jing Lu Zhuyun Dai Gustavo Hern\u00e1ndez \u00c1brego Ji Ma Vincent Y Zhao Yi Luan Keith B Hall Ming-Wei Chang et al. 2021. Large Dual Encoders Are Generalizable Retrievers. arXiv preprint arXiv:2112.07899 (2021)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_2_32_1","volume-title":"Dare: Data augmented relation extraction with gpt-2. arXiv preprint arXiv:2004.13845","author":"Papanikolaou Yannis","year":"2020","unstructured":"Yannis Papanikolaou and Andrea Pierleoni . 2020 . Dare: Data augmented relation extraction with gpt-2. arXiv preprint arXiv:2004.13845 (2020). Yannis Papanikolaou and Andrea Pierleoni. 2020. Dare: Data augmented relation extraction with gpt-2. arXiv preprint arXiv:2004.13845 (2020)."},{"key":"e_1_3_2_2_33_1","first-page":"d2","article-title":"H2oloo at TREC 2020: When all you got is a hammer... Deep Learning, Health Misinformation, and Precision Medicine","volume":"5","author":"Pradeep Ronak","year":"2020","unstructured":"Ronak Pradeep , Xueguang Ma , Xinyu Zhang , Hang Cui , Ruizhou Xu , Rodrigo Nogueira , and Jimmy Lin . 2020 . H2oloo at TREC 2020: When all you got is a hammer... Deep Learning, Health Misinformation, and Precision Medicine . Corpus 5 , d3 (2020), d2 . Ronak Pradeep, Xueguang Ma, Xinyu Zhang, Hang Cui, Ruizhou Xu, Rodrigo Nogueira, and Jimmy Lin. 2020. H2oloo at TREC 2020: When all you got is a hammer... Deep Learning, Health Misinformation, and Precision Medicine. Corpus 5, d3 (2020), d2.","journal-title":"Corpus"},{"key":"e_1_3_2_2_34_1","volume-title":"The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667","author":"Pradeep Ronak","year":"2021","unstructured":"Ronak Pradeep , Rodrigo Nogueira , and Jimmy Lin . 2021. The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667 ( 2021 ). Ronak Pradeep, Rodrigo Nogueira, and Jimmy Lin. 2021. The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667 (2021)."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ozk9MrX1hvA","author":"Qu Yanru","year":"2021","unstructured":"Yanru Qu , Dinghan Shen , Yelong Shen , Sandra Sajeev , Weizhu Chen , and Jiawei Han . 2021 . Co{DA}: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding . In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ozk9MrX1hvA Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Weizhu Chen, and Jiawei Han. 2021. Co{DA}: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ozk9MrX1hvA"},{"key":"e_1_3_2_2_36_1","unstructured":"Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young etal 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021).  Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_2_37_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , and Peter J Liu . 2020 . Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer . Journal of Machine Learning Research 21 (2020), 1 -- 67 . Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_38_1","volume-title":"Learning to Retrieve Passages without Supervision. arXiv preprint arXiv:2112.07708","author":"Ram Ori","year":"2021","unstructured":"Ori Ram , Gal Shachaf , Omer Levy , Jonathan Berant , and Amir Globerson . 2021. Learning to Retrieve Passages without Supervision. arXiv preprint arXiv:2112.07708 ( 2021 ). Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, and Amir Globerson. 2021. Learning to Retrieve Passages without Supervision. arXiv preprint arXiv:2112.07708 (2021)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa091"},{"key":"e_1_3_2_2_40_1","volume-title":"Okapi at TREC-3. NIST special publication 500225","author":"S.E. ROBERTSON, S. WALKER, S. JONES, M.M.","year":"1995","unstructured":"S.E. ROBERTSON, S. WALKER, S. JONES, M.M. HANCOCK-BEAULIEU, and M. GATFORD. 1995. Okapi at TREC-3. NIST special publication 500225 ( 1995 ), 109--123. S.E. ROBERTSON, S. WALKER, S. JONES, M.M. HANCOCK-BEAULIEU, and M. GATFORD. 1995. Okapi at TREC-3. NIST special publication 500225 (1995), 109--123."},{"key":"e_1_3_2_2_41_1","unstructured":"Victor Sanh Albert Webson Colin Raffel Stephen H. Bach Lintang Sutawika Zaid Alyafeai Antoine Chaffin Arnaud Stiegler Teven Le Scao Arun Raja Manan Dey M Saiful Bari Canwen Xu Urmish Thakker Shanya Sharma Sharma Eliza Szczechla Taewoon Kim Gunjan Chhablani Nihal Nayak Debajyoti Datta Jonathan Chang Mike Tian-Jian Jiang Han Wang Matteo Manica Sheng Shen Zheng Xin Yong Harshit Pandey Rachel Bawden ThomasWang Trishala Neeraj Jos Rozen Abheesht Sharma Andrea Santilli Thibault Fevry Jason Alan Fries Ryan Teehan Stella Biderman Leo Gao Tali Bers ThomasWolf and Alexander M. Rush. 2021. Multitask Prompted Training Enables Zero-Shot Task Generalization. arXiv:2110.08207 [cs.LG]  Victor Sanh Albert Webson Colin Raffel Stephen H. Bach Lintang Sutawika Zaid Alyafeai Antoine Chaffin Arnaud Stiegler Teven Le Scao Arun Raja Manan Dey M Saiful Bari Canwen Xu Urmish Thakker Shanya Sharma Sharma Eliza Szczechla Taewoon Kim Gunjan Chhablani Nihal Nayak Debajyoti Datta Jonathan Chang Mike Tian-Jian Jiang Han Wang Matteo Manica Sheng Shen Zheng Xin Yong Harshit Pandey Rachel Bawden ThomasWang Trishala Neeraj Jos Rozen Abheesht Sharma Andrea Santilli Thibault Fevry Jason Alan Fries Ryan Teehan Stella Biderman Leo Gao Tali Bers ThomasWolf and Alexander M. Rush. 2021. Multitask Prompted Training Enables Zero-Shot Task Generalization. arXiv:2110.08207 [cs.LG]"},{"key":"e_1_3_2_2_42_1","volume-title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. arXiv preprint arXiv:2112.01488","author":"Santhanam Keshav","year":"2021","unstructured":"Keshav Santhanam , Omar Khattab , Jon Saad-Falcon , Christopher Potts , and Matei Zaharia . 2021. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. arXiv preprint arXiv:2112.01488 ( 2021 ). Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2021. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. arXiv preprint arXiv:2112.01488 (2021)."},{"key":"e_1_3_2_2_43_1","volume-title":"Generating Datasets with Pretrained Language Models. arXiv preprint arXiv:2104.07540","author":"Schick Timo","year":"2021","unstructured":"Timo Schick and Hinrich Sch\u00fctze . 2021. Generating Datasets with Pretrained Language Models. arXiv preprint arXiv:2104.07540 ( 2021 ). Timo Schick and Hinrich Sch\u00fctze. 2021. Generating Datasets with Pretrained Language Models. arXiv preprint arXiv:2104.07540 (2021)."},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the 2021 Conference of the North American","author":"Schick Timo","year":"1865","unstructured":"Timo Schick and Hinrich Sch\u00fctze . 2021. It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners . 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 , 2339--2352. https:\/\/doi.org\/10. 1865 3\/v1\/2021.naacl-main.185 10.18653\/v1 Timo Schick and Hinrich Sch\u00fctze. 2021. It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners. 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, 2339--2352. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.185"},{"key":"e_1_3_2_2_45_1","unstructured":"Javad Pourmostafa Roshan Sharami Dimitar Shterionov and Pieter Spronck. 2022. Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts. arXiv:2112.06096 [cs.CL]  Javad Pourmostafa Roshan Sharami Dimitar Shterionov and Pieter Spronck. 2022. Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts. arXiv:2112.06096 [cs.CL]"},{"key":"e_1_3_2_2_46_1","unstructured":"Nandan Thakur Nils Reimers Andreas R\u00fcckl\u00e9 Abhishek Srivastava and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ  Nandan Thakur Nils Reimers Andreas R\u00fcckl\u00e9 Abhishek Srivastava and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_2_47_1","volume-title":"Overview of the TREC 2004 Robust Retrieval Track. https:\/\/doi.org\/10","author":"Voorhees Ellen","year":"2005","unstructured":"Ellen Voorhees . 2005 . Overview of the TREC 2004 Robust Retrieval Track. https:\/\/doi.org\/10 .6028\/NIST.SP.500--261 10.6028\/NIST.SP.500--261 Ellen Voorhees. 2005. Overview of the TREC 2004 Robust Retrieval Track. https:\/\/doi.org\/10.6028\/NIST.SP.500--261"},{"key":"e_1_3_2_2_48_1","volume-title":"Overview of TREC","author":"Voorhees Ellen M.","year":"2004","unstructured":"Ellen M. Voorhees . 2004 . Overview of TREC 2004. In TREC. Ellen M. Voorhees. 2004. Overview of TREC 2004. In TREC."},{"key":"e_1_3_2_2_49_1","volume-title":"Overview of the Eighth Text REtrieval Conference (TREC-8). In TREC.","author":"Ellen","unstructured":"Ellen M. Voorhees and Donna K. Harman. 1999 . Overview of the Eighth Text REtrieval Conference (TREC-8). In TREC. Ellen M. Voorhees and Donna K. Harman. 1999. Overview of the Eighth Text REtrieval Conference (TREC-8). In TREC."},{"key":"e_1_3_2_2_50_1","volume-title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval. arXiv preprint arXiv:2112.07577","author":"Wang Kexin","year":"2021","unstructured":"Kexin Wang , Nandan Thakur , Nils Reimers , and Iryna Gurevych . 2021 . GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval. arXiv preprint arXiv:2112.07577 (2021). Kexin Wang, Nandan Thakur, Nils Reimers, and Iryna Gurevych. 2021. GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval. arXiv preprint arXiv:2112.07577 (2021)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009934"},{"key":"e_1_3_2_2_52_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gEZrGCozdqR","author":"Wei Jason","year":"2022","unstructured":"Jason Wei , Maarten Bosma , Vincent Zhao , Kelvin Guu , Adams Wei Yu , Brian Lester , Nan Du , Andrew M. Dai , and Quoc V Le . 2022 . Finetuned Language Models are Zero-Shot Learners . In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gEZrGCozdqR Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V Le. 2022. Finetuned Language Models are Zero-Shot Learners. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.1"},{"key":"e_1_3_2_2_54_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 1008--1025","author":"Yang Yiben","year":"2020","unstructured":"Yiben Yang , Chaitanya Malaviya , Jared Fernandez , Swabha Swayamdipta , Ronan Le Bras , Ji-Ping Wang , Chandra Bhagavatula , Yejin Choi , and Doug Downey . 2020 . G-DAug: Generative Data Augmentation for Commonsense Reasoning . In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 1008--1025 . Yiben Yang, Chaitanya Malaviya, Jared Fernandez, Swabha Swayamdipta, Ronan Le Bras, Ji-Ping Wang, Chandra Bhagavatula, Yejin Choi, and Doug Downey. 2020. G-DAug: Generative Data Augmentation for Commonsense Reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings. 1008--1025."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401317"},{"key":"e_1_3_2_2_56_1","unstructured":"Tiezheng Yu Zihan Liu and Pascale Fung. 2021. AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization. arXiv:2103.11332 [cs.CL]  Tiezheng Yu Zihan Liu and Pascale Fung. 2021. AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization. arXiv:2103.11332 [cs.CL]"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531863","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:27Z","timestamp":1750183827000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":56,"alternative-id":["10.1145\/3477495.3531863","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531863","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}