English

Multi-Source Domain Adaptation with Mixture of Experts

Computation and Language 2018-10-17 v2

Abstract

We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer.

Keywords

Cite

@article{arxiv.1809.02256,
  title  = {Multi-Source Domain Adaptation with Mixture of Experts},
  author = {Jiang Guo and Darsh J Shah and Regina Barzilay},
  journal= {arXiv preprint arXiv:1809.02256},
  year   = {2018}
}

Comments

11 pages, EMNLP 2018

R2 v1 2026-06-23T03:57:26.350Z