Multi-Source Domain Adaptation with Mixture of Experts
This addresses the problem of negative transfer in multi-source domain adaptation for NLP tasks, offering a robust solution for practitioners.
The paper tackles unsupervised domain adaptation from multiple sources by proposing a mixture-of-experts approach that learns a metric to combine predictors based on target-source relationships, achieving consistent performance improvements over baselines in sentiment analysis and part-of-speech tagging.
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.