{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:25:53Z","timestamp":1749533153703,"version":"3.38.0"},"reference-count":25,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"vor","delay-in-days":52,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>In this paper, we study cross-domain relation extraction. Since new data mapping to feature spaces always differs from the previously seen data due to a domain shift, few-shot relation extraction often perform poorly. To solve the problems caused by cross-domain, we propose a method for combining the pure entity, relation labels and adversarial (PERLA). We first use entities and complete sentences for separate encoding to obtain context-independent entity features. Then, we combine relation labels which are useful for relation extraction to mitigate context noise. We combine adversarial to reduce the noise caused by cross-domain. We conducted experiments on the publicly available cross-domain relation extraction dataset Fewrel 2.0[1]\u2460, and the results show that our approach improves accuracy and has better transferability for better adaptation to cross-domain tasks.<\/jats:p>","DOI":"10.1162\/dint_a_00190","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T01:04:42Z","timestamp":1677027882000},"page":"807-823","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":6,"title":["Three Heads Better than One: Pure Entity, Relation Label and Adversarial Training for Cross-domain Few-shot Relation Extraction"],"prefix":"10.3724","volume":"5","author":[{"given":"Wenlong","family":"Fang","sequence":"first","affiliation":[]},{"given":"Chunping","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Qiang","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"2026","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"2023091215375297700_ref1","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1649","article-title":"FewRel 2.0: Towards more challenging few-shot relation classification","volume-title":"arXiv preprint arXiv:1910.07124","author":"Gao","year":"2019"},{"key":"2023091215375297700_ref2","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1514","article-title":"Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation","volume-title":"arXiv preprint arXiv:1810.10147","author":"Han","year":"2018"},{"key":"2023091215375297700_ref3","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"International Conference on Machine Learning","author":"Santoro","year":"2016"},{"key":"2023091215375297700_ref4","article-title":"Matching networks for one shot learning","volume-title":"Advances in Neural Information Processing Systems 29","author":"Vinyals","year":"2016"},{"key":"2023091215375297700_ref5","first-page":"1199","article-title":"Learning to compare: Relation network for few-shot learning","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sung","year":"2018"},{"key":"2023091215375297700_ref6","volume":"30","author":"Snell","year":"2017","journal-title":"Prototypical networks for few-shot learning"},{"key":"2023091215375297700_ref7","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.emnlp-main.298","article-title":"Learning from context or names? an empirical study on neural relation extraction","volume-title":"arXiv preprint arXiv:2010.01923","author":"Peng","year":"2020"},{"key":"2023091215375297700_ref8","article-title":"Optimization as a model for few-shot learning","volume-title":"International Conference on Learning Representations","author":"Ravi","year":"2017"},{"key":"2023091215375297700_ref9","first-page":"2554","article-title":"Meta networks","volume-title":"International Conference on Machine Learning","author":"Munkhdalai","year":"2017"},{"key":"2023091215375297700_ref10","article-title":"Meta-learning: A survey","volume-title":"arXiv preprint arXiv:1810.03548","author":"Vanschoren","year":"2018"},{"key":"2023091215375297700_ref11","first-page":"12365","article-title":"Meta-learning of neural architectures for few-shot learning","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Elsken","year":"2020"},{"key":"2023091215375297700_ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International Conference on Machine Learning","author":"Finn","year":"2017"},{"key":"2023091215375297700_ref13","article-title":"Bayesian model-agnostic meta-learning","volume":"31","author":"Yoon","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023091215375297700_ref14","first-page":"7867","article-title":"Few-shot relation extraction via bayesian metalearning on relation graphs","volume-title":"International Conference on Machine Learning","author":"Qu","year":"2020"},{"issue":"1","key":"2023091215375297700_ref15","article-title":"Siamese neural networks for one-shot image recognition","volume":"2","author":"Koch","year":"2015","journal-title":"ICML Deep Learning Workshop"},{"key":"2023091215375297700_ref16","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1277","article-title":"Multi-level matching and aggregation network for few-shot relation classification","volume-title":"arXiv preprint arXiv:1906.06678","author":"Ye","year":"2019"},{"issue":"01","key":"2023091215375297700_ref17","doi-asserted-by":"crossref","first-page":"6407","DOI":"10.1609\/aaai.v33i01.33016407","article-title":"Hybrid attention-based prototypical networks for noisy few-shot relation classification","volume":"33","author":"Gao","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023091215375297700_ref18","article-title":"Few-shot learning with graph neural networks","volume-title":"arXiv preprint arXiv:1711.04043","author":"Garcia","year":"2017"},{"key":"2023091215375297700_ref19","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-3-030-84186-7_13","article-title":"From learning-to-match to learning-to-discriminate: Global prototype learning for few-shot relation classification","volume-title":"China National Conference on Chinese Computational Linguistics","author":"Liu","year":"2021"},{"key":"2023091215375297700_ref20","doi-asserted-by":"crossref","first-page":"227","DOI":"10.18653\/v1\/2020.clinicalnlp-1.25","article-title":"Learning from unlabelled data for clinical semantic textual similarity","volume-title":"Proceedings of the 3rd Clinical Natural Language Processing Workshop","author":"Wang","year":"2020"},{"key":"2023091215375297700_ref21","first-page":"624","article-title":"Inductive unsupervised domain adaptation for few-shot classification via clustering","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"Cong","year":"2020"},{"key":"2023091215375297700_ref22","article-title":"Deep contextualized word representations","volume-title":"arXiv preprint arXiv:1802.05365","author":"Neumann","year":"2018"},{"volume-title":"Improving language understanding by generative pretraining","year":"2018","author":"Radford","key":"2023091215375297700_ref23"},{"key":"2023091215375297700_ref24","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv preprint arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"2023091215375297700_ref25","article-title":"Ensemble making few-shot learning stronger","volume-title":"arXiv preprint arXiv:2105.11904","author":"Lin","year":"2021"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/807\/2158187\/dint_a_00190.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/807\/2158187\/dint_a_00190.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:43:50Z","timestamp":1741938230000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00190","relation":{},"ISSN":["2641-435X"],"issn-type":[{"type":"electronic","value":"2641-435X"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}