Multi-Source Domain Adaptation with Mixture of Experts

Jiang Guo, Darsh Shah, Regina Barzilay


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.
Anthology ID:
D18-1498
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4694–4703
Language:
URL:
https://aclanthology.org/D18-1498
DOI:
10.18653/v1/D18-1498
Bibkey:
Cite (ACL):
Jiang Guo, Darsh Shah, and Regina Barzilay. 2018. Multi-Source Domain Adaptation with Mixture of Experts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4694–4703, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Multi-Source Domain Adaptation with Mixture of Experts (Guo et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/D18-1498.pdf
Code
 jiangfeng1124/transfer