Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning

Nghia Ngo Trung, Linh Ngo Van, Thien Huu Nguyen


Abstract
A shift in data distribution can have a significant impact on performance of a text classification model. Recent methods addressing unsupervised domain adaptation for textual tasks typically extracted domain-invariant representations through balancing between multiple objectives to align feature spaces between source and target domains. While effective, these methods induce various new domain-sensitive hyperparameters, thus are impractical as large-scale language models are drastically growing bigger to achieve optimal performance. To this end, we propose to leverage meta-learning framework to train a neural network-based self-paced learning procedure in an end-to-end manner. Our method, called Meta Self-Paced Domain Adaption (MSP-DA), follows a novel but intuitive domain-shift variation of cluster assumption to derive the meta train-test dataset split based on the self-pacing difficulties of source domain’s examples. As a result, MSP-DA effectively leverages self-training and self-tuning domain-specific hyperparameters simultaneously throughout the learning process. Extensive experiments demonstrate our framework substantially improves performance on target domains, surpassing state-of-the-art approaches. Detailed analyses validate our method and provide insight into how each domain affects the learned hyperparameters.
Anthology ID:
2022.coling-1.420
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4741–4752
Language:
URL:
https://aclanthology.org/2022.coling-1.420
DOI:
Bibkey:
Cite (ACL):
Nghia Ngo Trung, Linh Ngo Van, and Thien Huu Nguyen. 2022. Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4741–4752, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning (Trung et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.420.pdf