Multi-Source Domain Adaptation with Mixture of Experts
© 2018 Association for Computational Linguistics 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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association for Computational Linguistics (ACL),
2021-11-05T11:25:18Z.
|
| Subjects: | |
| Online Access: | Get fulltext |
| Summary: | © 2018 Association for Computational Linguistics 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.1 |
|---|