SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy Towards Cross-Domain Sentiment Classification (Student Abstract)

AAAI 2020 pp. 13763-13764

doi:10.1609/AAAI.V34I10.7153 /aaai/2020/cao2020aaai-satnet/

Abstract

In recent years, domain adaptation tasks have attracted much attention, especially, the task of cross-domain sentiment classification (CDSC). In this paper, we propose a novel domain adaptation method called Symmetric Adversarial Transfer Network (SATNet). Experiments on the Amazon reviews dataset demonstrate the effectiveness of SATNet.

PDF AAAI Semantic Scholar

Cite

Text

Cao and Xu. "SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy Towards Cross-Domain Sentiment Classification (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7153

Markdown

[Cao and Xu. "SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy Towards Cross-Domain Sentiment Classification (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/cao2020aaai-satnet/) doi:10.1609/AAAI.V34I10.7153

BibTeX

@inproceedings{cao2020aaai-satnet,
  title     = {{SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy Towards Cross-Domain Sentiment Classification (Student Abstract)}},
  author    = {Cao, Yu and Xu, Hua},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13763-13764},
  doi       = {10.1609/AAAI.V34I10.7153},
  url       = {https://mlanthology.org/aaai/2020/cao2020aaai-satnet/}
}