Neural Unsupervised Domain Adaptation in NLPA Survey

Alan Ramponi, Barbara Plank


Abstract
Deep neural networks excel at learning from labeled data and achieve state-of-the-art results on a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a challenge. Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data. This is a more challenging yet a more widely applicable setup. We outline methods, from early traditional non-neural methods to pre-trained model transfer. We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention. Lastly, we outline future directions, particularly the broader need for out-of-distribution generalization of future NLP.
Anthology ID:
2020.coling-main.603
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6838–6855
Language:
URL:
https://aclanthology.org/2020.coling-main.603
DOI:
10.18653/v1/2020.coling-main.603
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.603.pdf
Code
 bplank/awesome-neural-adaptation-in-NLP
Data
Penn Treebank