TY - GEN
T1 - Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
AU - Han, Cheng Cheng
AU - Fan, Zeqiu
AU - Zhang, Dongxiang
AU - Qiu, Minghui
AU - Gao, Ming
AU - Zhou, Aoying
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. In this paper, we propose a novel meta-learning framework integrated with an adversarial domain adaptation network, aiming to improve the adaptive ability of the model and generate high-quality text embedding for new classes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, the accuracy of 1-shot and 5-shot classification on the dataset of 20 Newsgroups is boosted from 52.1% to 59.6%, and from 68.3% to 77.8%, respectively.
AB - Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. In this paper, we propose a novel meta-learning framework integrated with an adversarial domain adaptation network, aiming to improve the adaptive ability of the model and generate high-quality text embedding for new classes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, the accuracy of 1-shot and 5-shot classification on the dataset of 20 Newsgroups is boosted from 52.1% to 59.6%, and from 68.3% to 77.8%, respectively.
UR - https://www.scopus.com/pages/publications/85123960785
U2 - 10.18653/v1/2021.findings-acl.145
DO - 10.18653/v1/2021.findings-acl.145
M3 - 会议稿件
AN - SCOPUS:85123960785
T3 - Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
SP - 1664
EP - 1673
BT - Findings of the Association for Computational Linguistics
A2 - Zong, Chengqing
A2 - Xia, Fei
A2 - Li, Wenjie
A2 - Navigli, Roberto
PB - Association for Computational Linguistics (ACL)
T2 - Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Y2 - 1 August 2021 through 6 August 2021
ER -