{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:44:17Z","timestamp":1781279057224,"version":"3.54.1"},"reference-count":73,"publisher":"MIT Press - Journals","license":[{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"content-version":"vor","delay-in-days":100,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Natural Language Processing algorithms have made incredible progress, but they still struggle when applied to out-of-distribution examples. We address a challenging and underexplored version of this domain adaptation problem, where an algorithm is trained on several source domains, and then applied to examples from unseen domains that are unknown at training time. Particularly, no examples, labeled or unlabeled, or any other knowledge about the target domain are available to the algorithm at training time. We present PADA: An example-based autoregressive Prompt learning algorithm for on-the-fly Any-Domain Adaptation, based on the T5 language model. Given a test example, PADA first generates a unique prompt for it and then, conditioned on this prompt, labels the example with respect to the NLP prediction task. PADA is trained to generate a prompt that is a token sequence of unrestricted length, consisting of Domain Related Features (DRFs) that characterize each of the source domains. Intuitively, the generated prompt is a unique signature that maps the test example to a semantic space spanned by the source domains. In experiments with 3 tasks (text classification and sequence tagging), for a total of 14 multi-source adaptation scenarios, PADA substantially outperforms strong baselines.1<\/jats:p>","DOI":"10.1162\/tacl_a_00468","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T19:40:37Z","timestamp":1649706037000},"page":"414-433","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":37,"title":["PADA: Example-based Prompt Learning for on-the-fly Adaptation to\n                    Unseen Domains"],"prefix":"10.1162","volume":"10","author":[{"given":"Eyal","family":"Ben-David","sequence":"first","affiliation":[{"name":"Technion - Israel Institute of Technology, Israel. eyalbd12@campus.technion.ac.il"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadav","family":"Oved","sequence":"additional","affiliation":[{"name":"Technion - Israel Institute of Technology, Israel. nadavo@campus.technion.ac.il"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roi","family":"Reichart","sequence":"additional","affiliation":[{"name":"Technion - Israel Institute of Technology, Israel. roiri@technion.ac.il"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2022,4,11]]},"reference":[{"key":"2022041119402771200_bib1","article-title":"Invariant risk\n                        minimization","author":"Arjovsky","year":"2019","journal-title":"CoRR"},{"key":"2022041119402771200_bib2","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1162\/tacl_a_00328","article-title":"Perl: Pivot-based domain adaptation for\n                        pre-trained deep contextualized embedding models","volume":"8","author":"Ben-David","year":"2020","journal-title":"Transactions of the Association for Computational\n                        Linguistics"},{"key":"2022041119402771200_bib3","article-title":"Biographies, Bollywood, boom-boxes and\n                        blenders: Domain adaptation for sentiment classification","volume-title":"ACL 2007, Proceedings of the 45th Annual Meeting of the Association\n                        for Computational Linguistics, June 23\u201330, 2007, Prague, Czech\n                        Republic","author":"Blitzer","year":"2007"},{"key":"2022041119402771200_bib4","article-title":"Zero-shot domain adaptation: A multi-view\n                        approach","author":"Blitzer","year":"2009"},{"key":"2022041119402771200_bib5","doi-asserted-by":"publisher","first-page":"120","DOI":"10.3115\/1610075.1610094","article-title":"Domain adaptation with structural\n                        correspondence learning","volume-title":"EMNLP 2006, Proceedings\n                        of the 2006 Conference on Empirical Methods in Natural Language Processing,\n                        22\u201323 July 2006, Sydney, Australia","author":"Blitzer","year":"2006"},{"key":"2022041119402771200_bib6","doi-asserted-by":"publisher","first-page":"632","DOI":"10.18653\/v1\/D15-1075","article-title":"A large annotated corpus for learning\n                        natural language inference","volume-title":"Proceedings of the\n                        2015 Conference on Empirical Methods in Natural Language Processing,\n                        EMNLP","author":"Bowman","year":"2015"},{"key":"2022041119402771200_bib7","article-title":"Language models are few-shot\n                        learners","volume-title":"Advances in Neural Information\n                        Processing Systems 33: Annual Conference on Neural Information Processing\n                        Systems 2020, NeurIPS 2020, December 6\u201312, 2020,\n                    virtual","author":"Brown","year":"2020"},{"key":"2022041119402771200_bib8","article-title":"Marginalized denoising autoencoders for domain\n                        adaptation","volume-title":"Proceedings of the 29th International\n                        Conference on Machine Learning, ICML 2012, Edinburgh, Scotland, UK, June 26\n                        \u2013 July 1, 2012","author":"Chen","year":"2012"},{"key":"2022041119402771200_bib9","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.18653\/v1\/N18-1111","article-title":"Multinomial adversarial networks for\n                        multi-domain text classification","volume-title":"Proceedings of\n                        the 2018 Conference of the North American Chapter of the Association for\n                        Computational Linguistics: Human Language Technologies, NAACL- HLT","author":"Chen","year":"2018"},{"key":"2022041119402771200_bib10","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1613\/jair.1872","article-title":"Domain adaptation for statistical\n                        classifiers","volume":"26","author":"Daum\u00e9","year":"2006","journal-title":"Journal of Artificial Intelligence\n                        Research"},{"key":"2022041119402771200_bib11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional\n                        transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of\n                        the Association for Computational Linguistics: Human Language Technologies,\n                        NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long\n                        and Short Papers)","author":"Devlin","year":"2019"},{"key":"2022041119402771200_bib12","first-page":"59:1\u201359:35","article-title":"Domain-adversarial training of neural\n                        networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The Journal of Machine Learning\n                        Research"},{"key":"2022041119402771200_bib13","first-page":"3816","article-title":"Making pre-trained language models better few-shot\n                        learners","volume-title":"Proceedings of the 59th Annual Meeting\n                        of the Association for Computational Linguistics and the 11th International\n                        Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1:\n                        Long Papers), Virtual Event, August 1\u20136, 2021","author":"Gao","year":"2021"},{"key":"2022041119402771200_bib14","first-page":"513","article-title":"Domain adaptation for large- scale\n                        sentiment classification: A deep learning approach","volume-title":"Proceedings of the 28th International Conference on Machine\n                        Learning, ICML 2011, Bellevue, Washington, USA, June 28 \u2013 July 2,\n                        2011","author":"Glorot","year":"2011"},{"key":"2022041119402771200_bib15","doi-asserted-by":"publisher","first-page":"7035","DOI":"10.18653\/v1\/2020.emnlp-main.572","article-title":"Unified feature and instance based domain adaptation for\n                        aspect-based sentiment analysis","volume-title":"Proceedings of\n                        the 2020 Conference on Empirical Methods in Natural Language Processing,\n                        EMNLP","author":"Gong","year":"2020"},{"key":"2022041119402771200_bib16","doi-asserted-by":"publisher","first-page":"4694","DOI":"10.18653\/v1\/D18-1498","article-title":"Multi-source domain adaptation with\n                        mixture of experts","volume-title":"Proceedings of the 2018\n                        Conference on Empirical Methods in Natural Language Processing, Brussels,\n                        Belgium, October 31 \u2013 November 4, 2018","author":"Guo","year":"2018"},{"key":"2022041119402771200_bib17","first-page":"4237","article-title":"Unsupervised domain adaptation of\n                        contextualized embeddings for sequence labeling","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural\n                        Language Processing and the 9th International Joint Conference on Natural\n                        Language Processing, EMNLP- IJCNLP 2019, Hong Kong, China, November\n                        3\u20137, 2019","author":"Han","year":"2019"},{"key":"2022041119402771200_bib18","article-title":"PTR: Prompt tuning with rules for text\n                        classification","author":"Han","year":"2021","journal-title":"CoRR"},{"key":"2022041119402771200_bib19","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.18653\/v1\/2021.eacl-main.316","article-title":"Bertese: Learning to speak to\n                        BERT","volume-title":"Proceedings of the 16th Conference of the\n                        European Chapter of the Association for Computational Linguistics: Main\n                        Volume, EACL","author":"Haviv","year":"2021"},{"key":"2022041119402771200_bib20","first-page":"168","article-title":"Mining and summarizing customer reviews","volume-title":"Proceedings of the 10th ACM SIGKDD International Conference on\n                        Knowledge Discovery and Data Mining, Seattle, Washington, USA, August\n                        22\u201325, 2004","author":"Minqing","year":"2004"},{"key":"2022041119402771200_bib21","first-page":"2034","article-title":"Does distributionally robust supervised\n                        learning give robust classifiers?","volume-title":"Proceedings of\n                        the 35th International Conference on Machine Learning, ICML 2018,\n                        Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315,\n                    2018","author":"Weihua","year":"2018"},{"key":"2022041119402771200_bib22","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1162\/tacl_a_00324","article-title":"How can we know what language models\n                        know","volume":"8","author":"Jiang","year":"2020","journal-title":"Transactions of the Association for\n                        Computational Linguistics"},{"key":"2022041119402771200_bib23","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1162\/tacl_a_00324","article-title":"Domain attention with an ensemble of experts","volume-title":"Proceedings of the 55th Annual Meeting of the Association for\n                        Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 \u2013\n                        August 4, Volume 1: Long Papers","author":"Kim","year":"2017"},{"key":"2022041119402771200_bib24","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd International Conference on Learning Representations, ICLR 2015,\n                        San Diego, CA, USA, May 7\u20139, 2015, Conference Track\n                        Proceedings","author":"Kingma","year":"2015"},{"key":"2022041119402771200_bib25","article-title":"WILDS: A benchmark of in-the-wild distribution\n                        shifts","author":"Koh","year":"2020","journal-title":"CoRR"},{"key":"2022041119402771200_bib26","doi-asserted-by":"publisher","first-page":"219","DOI":"10.18653\/v1\/2021.emnlp-main.20","article-title":"DILBERT: Customized pre-training for\n                        domain adaptation with category shift, with an application to aspect\n                        extraction","volume-title":"Proceedings of the 2021 Conference on\n                        Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\n                        \/ Punta Cana, Dominican Republic, 7\u201311 November, 2021","author":"Lekhtman","year":"2021"},{"key":"2022041119402771200_bib27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243","article-title":"The power of scale for parameter-\n                        efficient prompt tuning","author":"Lester","year":"2021","journal-title":"CoRR"},{"key":"2022041119402771200_bib28","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence\n                        pre-training for natural language generation, translation, and\n                        comprehension","volume-title":"Proceedings of the 58th Annual\n                        Meeting of the Association for Computational Linguistics, ACL 2020, Online,\n                        July 5\u201310, 2020","author":"Lewis","year":"2020"},{"key":"2022041119402771200_bib29","first-page":"257","article-title":"Multi- domain sentiment classification","volume-title":"ACL 2008, Proceedings of the 46th Annual Meeting of the Association\n                        for Computational Linguistics, June 15\u201320, 2008, Columbus, Ohio, USA,\n                        Short Papers","author":"Li","year":"2008"},{"key":"2022041119402771200_bib30","first-page":"4582","article-title":"Prefix- tuning: Optimizing continuous prompts\n                        for generation","volume-title":"Proceedings of the 59th Annual\n                        Meeting of the Association for Computational Linguistics and the 11th\n                        International Joint Conference on Natural Language Processing, ACL\/IJCNLP\n                        2021, (Volume 1: Long Papers), Virtual Event, August 1\u20136,\n                        2021","author":"Li","year":"2021"},{"key":"2022041119402771200_bib31","article-title":"Rouge: A package for automatic evaluation of\n                        summaries","volume-title":"Proceedings of Workshop on Text\n                        Summarization Branches Out, Post Conference Workshop of ACL\n                    2004","author":"Lin","year":"2004"},{"key":"2022041119402771200_bib32","article-title":"Pre-train, prompt, and predict: A\n                        systematic survey of prompting methods in natural language\n                        processing","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"2022041119402771200_bib33","article-title":"GPT understands, too","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"2022041119402771200_bib34","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/1458082.1458099","article-title":"Transfer learning from multiple source domains via consensus\n                        regularization","volume-title":"Proceedings of the 17th ACM\n                        Conference on Information and Knowledge Management, CIKM 2008, Napa Valley,\n                        California, USA, October 26\u201330, 2008","author":"Luo","year":"2008"},{"key":"2022041119402771200_bib35","first-page":"28","article-title":"Automatic domain adaptation for\n                        parsing","volume-title":"Human Language Technologies: Conference\n                        of the North American Chapter of the Association of Computational\n                        Linguistics, Proceedings, June 2\u20134, 2010, Los Angeles, California,\n                        USA","author":"McClosky","year":"2010"},{"key":"2022041119402771200_bib36","first-page":"10","article-title":"Domain generalization via invariant\n                        feature representation","volume-title":"Proceedings of the 30th\n                        International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA,\n                        16\u201321 June 2013","author":"Muandet","year":"2013"},{"key":"2022041119402771200_bib37","first-page":"151","article-title":"Domain robustness in neural machine\n                        translation","volume-title":"Proceedings of the 14th Conference\n                        of the Association for Machine Translation in the Americas, AMTA 2020,\n                        Virtual, October 6\u20139, 2020","author":"M\u00fcller","year":"2020"},{"key":"2022041119402771200_bib38","doi-asserted-by":"publisher","first-page":"4226","DOI":"10.18653\/v1\/D19-1432","article-title":"Distributionally robust language\n                        modeling","volume-title":"Proceedings of the 2019 Conference on\n                        Empirical Methods in Natural Language Processing and the 9th International\n                        Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong\n                        Kong, China, November 3\u20137, 2019","author":"Oren","year":"2019"},{"key":"2022041119402771200_bib39","article-title":"Continual learning with\n                        hypernetworks","volume-title":"8th International Conference on\n                        Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April\n                        26\u201330, 2020","author":"von Oswald","year":"2020"},{"key":"2022041119402771200_bib40","first-page":"1410","article-title":"Zero-shot learning with semantic output\n                        codes","volume-title":"Advances in Neural Information Processing\n                        Systems 22: 23rd Annual Conference on Neural Information Processing Systems\n                        2009. Proceedings of a meeting held 7\u201310 December 2009, Vancouver,\n                        British Columbia, Canada","author":"Palatucci","year":"2009"},{"key":"2022041119402771200_bib41","first-page":"751","article-title":"Cross-domain sentiment classification via spectral feature\n                        alignment","volume-title":"Proceedings of the 19th International\n                        Conference on World Wide Web, WWW 2010, Raleigh, North Carolina, USA, April\n                        26\u201330, 2010","author":"Pan","year":"2010"},{"key":"2022041119402771200_bib42","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1007\/978-3-030-01252-6_47","article-title":"Zero-shot deep domain\n                        adaptation","volume-title":"Computer Vision - ECCV 2018 - 15th\n                        European Conference, Munich, Germany, September 8\u201314, 2018,\n                        Proceedings, Part XI","author":"Peng","year":"2018"},{"key":"2022041119402771200_bib43","doi-asserted-by":"publisher","first-page":"7654","DOI":"10.18653\/v1\/2020.emnlp-main.617","article-title":"MAD\u2013X: An adapter- based framework for\n                        multi-task cross-lingual transfer","volume-title":"Proceedings of\n                        the 2020 Conference on Empirical Methods in Natural Language Processing,\n                        EMNLP","author":"Pfeiffer","year":"2020"},{"key":"2022041119402771200_bib44","doi-asserted-by":"publisher","first-page":"27","DOI":"10.3115\/v1\/S14-2004","article-title":"Semeval-2014 task 4: Aspect based\n                        sentiment analysis","volume-title":"Proceedings of the 8th\n                        International Workshop on Semantic Evaluation, SemEval@COLING 2014, Dublin,\n                        Ireland, August 23\u201324, 2014","author":"Pontiki","year":"2014"},{"key":"2022041119402771200_bib45","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified\n                        text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine\n                        Learning Research"},{"key":"2022041119402771200_bib46","doi-asserted-by":"publisher","first-page":"6838","DOI":"10.18653\/v1\/2020.coling-main.603","article-title":"Neural unsupervised domain adaptation in NLP -\n                        A survey","volume-title":"Proceedings of the 28th International\n                        Conference on Computational Linguistics, COLING 2020, Barcelona, Spain\n                        (Online), December 8\u201313, 2020","author":"Ramponi","year":"2020"},{"key":"2022041119402771200_bib47","article-title":"Self- training for enhancement and domain\n                        adaptation of statistical parsers trained on small datasets","volume-title":"ACL 2007, Proceedings of the 45th Annual Meeting of the Association\n                        for Computational Linguistics, June 23\u201330, 2007, Prague, Czech\n                        Republic","author":"Reichart","year":"2007"},{"key":"2022041119402771200_bib48","unstructured":"Mark B.\n              Ring\n            \n          . 1995.\n                        Continual learning in reinforcement environments. Ph.D.\n                    thesis, University of Texas at Austin,\n                        TX, USA."},{"key":"2022041119402771200_bib49","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073472","article-title":"Supervised and unsupervised PCFG\n                        adaptation to novel domains","volume-title":"Human Language\n                        Technology Conference of the North American Chapter of the Association for\n                        Computational Linguistics, HLT-NAACL 2003, Edmonton, Canada, May 27 \u2013\n                        June 1, 2003","author":"Roark","year":"2003"},{"key":"2022041119402771200_bib50","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.18653\/v1\/2020.emnlp-main.194","article-title":"Multicqa: Zero-shot transfer of\n                        self-supervised text matching models on a massive scale","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural\n                        Language Processing, EMNLP","author":"R\u00fcckl\u00e9","year":"2020"},{"key":"2022041119402771200_bib51","first-page":"1434","article-title":"Improved parsing and POS tagging using\n                        inter-sentence consistency constraints","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in\n                        Natural Language Processing and Computational Natural Language Learning,\n                        EMNLP- CoNLL 2012, July 12\u201314, 2012, Jeju Island, Korea","author":"Rush","year":"2012"},{"key":"2022041119402771200_bib52","article-title":"Distributionally robust neural\n                        networks","volume-title":"8th International Conference on\n                        Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April\n                        26\u201330, 2020","author":"Sagawa","year":"2020"},{"key":"2022041119402771200_bib53","article-title":"Distilbert, a distilled version of BERT: Smaller, faster,\n                        cheaper and lighter","author":"Sanh","year":"2019","journal-title":"CoRR"},{"key":"2022041119402771200_bib54","doi-asserted-by":"publisher","first-page":"2627","DOI":"10.18653\/v1\/2021.naacl-main.208","article-title":"How many data points is a prompt worth?","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of\n                        the Association for Computational Linguistics: Human Language Technologies,\n                        NAACL-HLT","author":"Scao","year":"2021"},{"key":"2022041119402771200_bib55","doi-asserted-by":"publisher","first-page":"255","DOI":"10.18653\/v1\/2021.eacl-main.20","article-title":"Exploiting cloze-questions for few-shot\n                        text classification and natural language inference","volume-title":"Proceedings of the 16th Conference of the European Chapter of the\n                        Association for Computational Linguistics: Main Volume, EACL","author":"Schick","year":"2021"},{"key":"2022041119402771200_bib56","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1162\/tacl_a_00162","article-title":"FLORS: Fast and simple domain adaptation\n                        for part-of-speech tagging","volume":"2","author":"Schnabel","year":"2014","journal-title":"Transactions of the\n                        Association for Computational Linguistics"},{"key":"2022041119402771200_bib57","doi-asserted-by":"publisher","first-page":"4222","DOI":"10.18653\/v1\/2020.emnlp-main.346","article-title":"Autoprompt: Eliciting knowledge from language\n                        models with automatically generated prompts","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural\n                        Language Processing, EMNLP 2020, Online, November 16\u201320,\n                        2020","author":"Shin","year":"2020"},{"key":"2022041119402771200_bib58","article-title":"Conditioned natural language generation using only\n                        unconditioned language model: An exploration","author":"Sun","year":"2020","journal-title":"CoRR"},{"key":"2022041119402771200_bib59","first-page":"575","article-title":"Sentence and expression level annotation\n                        of opinions in user-generated discourse","volume-title":"ACL\n                        2010, Proceedings of the 48th Annual Meeting of the Association for\n                        Computational Linguistics, July 11\u201316, 2010, Uppsala,\n                    Sweden","author":"Toprak","year":"2010"},{"key":"2022041119402771200_bib60","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems 30: Annual\n                        Conference on Neural Information Processing Systems 2017, December\n                        4\u20139, 2017, Long Beach, CA, USA","author":"Vaswani","year":"2017"},{"key":"2022041119402771200_bib61","article-title":"Diverse beam search: Decoding diverse\n                        solutions from neural sequence models","author":"Vijayakumar","year":"2016","journal-title":"CoRR"},{"key":"2022041119402771200_bib62","article-title":"On calibration and out-of- domain\n                        generalization","volume-title":"Thirty-Fifth Conference on Neural\n                        Information Processing Systems","author":"Wald","year":"2021"},{"key":"2022041119402771200_bib63","first-page":"1112","article-title":"A broad-coverage challenge corpus for\n                        sentence understanding through inference","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of\n                        the Association for Computational Linguistics: Human Language Technologies,\n                        Volume 1 (Long Papers)","author":"Williams","year":"2018"},{"key":"2022041119402771200_bib64","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","article-title":"Transformers: State-of-the-art natural language\n                        processing","volume-title":"Proceedings of the 2020 Conference on\n                        Empirical Methods in Natural Language Processing: System\n                        Demonstrations","author":"Wolf","year":"2020"},{"key":"2022041119402771200_bib65","doi-asserted-by":"publisher","first-page":"7963","DOI":"10.18653\/v1\/2020.emnlp-main.639","article-title":"Transformer based multi-source domain\n                        adaptation","volume-title":"Proceedings of the 2020 Conference on\n                        Empirical Methods in Natural Language Processing (EMNLP)","author":"Wright","year":"2020"},{"key":"2022041119402771200_bib66","doi-asserted-by":"publisher","first-page":"538","DOI":"10.3115\/v1\/P14-2088","article-title":"Fast easy unsupervised domain adaptation\n                        with marginalized structured dropout","volume-title":"Proceedings\n                        of the 52nd Annual Meeting of the Association for Computational Linguistics,\n                        ACL 2014, June 22\u201327, 2014, Baltimore, MD, USA, Volume 2: Short\n                        Papers","author":"Yi","year":"2014"},{"key":"2022041119402771200_bib67","article-title":"Bertscore: Evaluating text generation with\n                        BERT","volume-title":"8th International Conference on Learning\n                        Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330,\n                        2020","author":"Zhang","year":"2020"},{"key":"2022041119402771200_bib68","article-title":"Multiple source domain adaptation with\n                        adversarial learning","volume-title":"6th International\n                        Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada,\n                        April 30 \u2013 May 3, 2018, Workshop Track Proceedings","author":"Zhao","year":"2018"},{"key":"2022041119402771200_bib69","doi-asserted-by":"publisher","first-page":"400","DOI":"10.18653\/v1\/K17-1040","article-title":"Neural structural correspondence learning\n                        for domain adaptation","volume-title":"Proceedings of the 21st\n                        Conference on Computational Natural Language Learning (CoNLL 2017),\n                        Vancouver, Canada, August 3\u20134, 2017","author":"Ziser","year":"2017"},{"key":"2022041119402771200_bib70","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.18653\/v1\/N18-1112","article-title":"Pivot based language modeling for improved\n                        neural domain adaptation","volume-title":"Proceedings of the 2018\n                        Conference of the North American Chapter of the Association for\n                        Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Ziser","year":"2018"},{"key":"2022041119402771200_bib71","doi-asserted-by":"publisher","first-page":"5895","DOI":"10.18653\/v1\/P19-1591","article-title":"Task refinement learning for improved\n                        accuracy and stability of unsupervised domain adaptation","volume-title":"Proceedings of the 57th Conference of the Association for\n                        Computational Linguistics, ACL","author":"Ziser","year":"2019"},{"key":"2022041119402771200_bib72","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-319-67217-5_8","article-title":"Exploiting context for rumour detection in\n                        social media","volume-title":"Social Informatics - 9th\n                        International Conference, SocInfo 2017, Oxford, UK, September 13\u201315,\n                        2017, Proceedings, Part I","author":"Zubiaga","year":"2017"},{"issue":"3","key":"2022041119402771200_bib73","doi-asserted-by":"publisher","first-page":"e0150989","DOI":"10.1371\/journal.pone.0150989","article-title":"Analysing how people orient to and spread\n                        rumours in social media by looking at conversational\n                    threads","volume":"11","author":"Zubiaga","year":"2016","journal-title":"PloS One"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00468\/2008061\/tacl_a_00468.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00468\/2008061\/tacl_a_00468.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T19:41:22Z","timestamp":1649706082000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00468\/110538\/PADA-Example-based-Prompt-Learning-for-on-the-fly"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00468","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}