{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:19:02Z","timestamp":1729635542291,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383453","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"1028-1035","source":"Crossref","is-referenced-by-count":0,"title":["Go Beyond Plain Fine-Tuning: Improving Pretrained Models for Social Commonsense"],"prefix":"10.1109","author":[{"given":"Ting-Yun","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthik","family":"Gopalakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Behnam","family":"Hedayatnia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dilek","family":"Hakkani-Tur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"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 arXiv 2005 06138"},{"key":"ref31","article-title":"Sentence encoders on stilts: Supplementary training on intermediate labeled-data tasks","author":"phang","year":"2018","journal-title":"arXiv preprint arXiv 1811 01088"},{"key":"ref30","article-title":"The winograd schema challenge","author":"levesque","year":"2012","journal-title":"Thirteenth International Conference on the Principles of Knowledge Representation and Reasoning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1335"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1407"},{"key":"ref34","article-title":"Don’t stop pretraining: Adapt language models to domains and tasks","author":"gururangan","year":"2020","journal-title":"arXiv preprint arXiv 2004 10491"},{"key":"ref10","article-title":"Dynamic knowledge graph construction for zero-shot commonsense question answering","author":"bosselut","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref11","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref12","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref13"},{"article-title":"Language models are unsupervised multitask learners","year":"2019","author":"radford","key":"ref14"},{"key":"ref15","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"arXiv preprint arXiv 1910 10335"},{"key":"ref16","article-title":"Unifiedqa: Crossing format boundaries with a single qa system","author":"khashabi","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref17","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"dodge","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref19","first-page":"1908","article-title":"Catastrophic forgetting meets negative transfer: Batch spectral shrinkage for safe transfer learning","author":"chen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref6","article-title":"Unsupervised common-sense question answering with self-talk","author":"shwartz","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref5","first-page":"8732","article-title":"Winogrande: An adversarial winograd schema challenge at scale","author":"sakaguchi","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.deelio-1.9"},{"key":"ref8","article-title":"How additional knowledge can improve natural language commonsense question answering?","author":"mitra","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1243"},{"key":"ref1","first-page":"4149","article-title":"CommonsenseQA: A question answering challenge targeting commonsense knowledge","author":"talmor","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref9","article-title":"Social commonsense reasoning with multi-head knowledge attention","author":"paul","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"wolpert","year":"1992","journal-title":"Neural Networks"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-13-2122-1","article-title":"Hierarchical attention flow for multiple-choice reading comprehension","author":"zhu","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref21","article-title":"Bidirectional attention flow for machine comprehension","author":"seo","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-1120"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383453.pdf?arnumber=9383453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:58Z","timestamp":1671715018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383453","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}