TY - GEN

T1 - Transformer Based Multi-Source Domain Adaptation

AU - Wright, Dustin

AU - Augenstein, Isabelle

PY - 2020

Y1 - 2020

N2 - In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain adaptation, where a model is trained on labelled data from multiple source domains and must make predictions on a domain for which no labelled data has been seen. Prior work with CNNs and RNNs has demonstrated the benefit of mixture of experts, where the predictions of multiple domain expert classifiers are combined; as well as domain adversarial training, to induce a domain agnostic representation space. Inspired by this, we investigate how such methods can be effectively applied to large pretrained transformer models. We find that domain adversarial training has an effect on the learned representations of these models while having little effect on their performance, suggesting that large transformer-based models are already relatively robust across domains. Additionally, we show that mixture of experts leads to significant performance improvements by comparing several variants of mixing functions, including one novel metric based on attention. Finally, we demonstrate that the predictions of large pretrained transformer based domain experts are highly homogenous, making it challenging to learn effective metrics for mixing their predictions.

AB - In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain adaptation, where a model is trained on labelled data from multiple source domains and must make predictions on a domain for which no labelled data has been seen. Prior work with CNNs and RNNs has demonstrated the benefit of mixture of experts, where the predictions of multiple domain expert classifiers are combined; as well as domain adversarial training, to induce a domain agnostic representation space. Inspired by this, we investigate how such methods can be effectively applied to large pretrained transformer models. We find that domain adversarial training has an effect on the learned representations of these models while having little effect on their performance, suggesting that large transformer-based models are already relatively robust across domains. Additionally, we show that mixture of experts leads to significant performance improvements by comparing several variants of mixing functions, including one novel metric based on attention. Finally, we demonstrate that the predictions of large pretrained transformer based domain experts are highly homogenous, making it challenging to learn effective metrics for mixing their predictions.

U2 - 10.18653/v1/2020.emnlp-main.639

DO - 10.18653/v1/2020.emnlp-main.639

M3 - Article in proceedings

SP - 7963

EP - 7974

BT - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

PB - Association for Computational Linguistics

T2 - The 2020 Conference on Empirical Methods in Natural Language Processing

Y2 - 16 November 2020 through 20 November 2020

ER -