{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T18:40:19Z","timestamp":1771008019074,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["NSF CISE-2223292"],"award-info":[{"award-number":["NSF CISE-2223292"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/icdmw58026.2022.00122","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:55:09Z","timestamp":1675882509000},"page":"941-946","source":"Crossref","is-referenced-by-count":1,"title":["STT: Soft Template Tuning for Few-Shot Adaptation"],"prefix":"10.1109","author":[{"given":"Ping","family":"Yu","sequence":"first","affiliation":[{"name":"University at Buffalo"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"University at Buffalo"}]},{"given":"Chunyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"given":"Ruiyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Adobe Research"}]},{"given":"Zhanpeng","family":"Jin","sequence":"additional","affiliation":[{"name":"University at Buffalo"}]},{"given":"Changyou","family":"Chen","sequence":"additional","affiliation":[{"name":"University at Buffalo"}]}],"member":"263","reference":[{"key":"ref1","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref4","author":"Liu","year":"2019","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"ref5","article-title":"Exploring the limits of trans-fer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"ref12","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"ref14","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"1907","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Making pre-trained language models better few-shot learners","author":"Gao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Online: Association for Computational Linguistics","author":"Wolf"},{"key":"ref17","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proceedings of the 2013 conference on empirical methods in natural language processing","author":"Socher"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-005-7880-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345577"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref24","article-title":"First quora dataset release: Question pairs","author":"Iyer","year":"2017","journal-title":"data. quora. com"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref26","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning. PMLR","author":"Houlsby"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref29","article-title":"Sentence encoders on stilts: Sup-plementary training on intermediate labeled-data tasks","author":"Phang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.468"},{"key":"ref31","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"Dodge","year":"2020","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Intermediate-task transfer learning with pretrained models for natural language understanding: When and why does it work?","author":"Pruksachatkun","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Revisiting few-sample bert fine-tuning","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.208"},{"key":"ref35","article-title":"Exploiting cloze questions for few shot text classification and natural language inference","author":"Schick","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.410"},{"key":"ref38","article-title":"Superglue: A stickier benchmark for general-purpose language understanding systems","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","location":"Orlando, FL, USA","start":{"date-parts":[[2022,11,28]]},"end":{"date-parts":[[2022,12,1]]}},"container-title":["2022 IEEE International Conference on Data Mining Workshops (ICDMW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10029378\/10029381\/10031195.pdf?arnumber=10031195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T10:56:01Z","timestamp":1707821761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10031195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icdmw58026.2022.00122","relation":{},"subject":[],"published":{"date-parts":[[2022,11]]}}}