Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification

  • Cheng Cheng Han
  • , Zeqiu Fan
  • , Dongxiang Zhang
  • , Minghui Qiu
  • , Ming Gao*
  • , Aoying Zhou
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

48 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationACL-IJCNLP 2021
EditorsChengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
PublisherAssociation for Computational Linguistics (ACL)
Pages1664-1673
Number of pages10
ISBN (Electronic)9781954085541
DOIs
StatePublished - 2021
EventFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021 - Virtual, Online
Duration: 1 Aug 20216 Aug 2021

Publication series

NameFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Conference

ConferenceFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021
CityVirtual, Online
Period1/08/216/08/21

Fingerprint

Dive into the research topics of 'Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification'. Together they form a unique fingerprint.

Cite this