Neural Unsupervised Domain Adaptation in NLP—A Survey

Alan Ramponi, Barbara Plank

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationThe 28th International Conference on Computational Linguistics
PublisherAssociation for Computational Linguistics
Publication dateDec 2020
Publication statusPublished - Dec 2020

Keywords

  • Unsupervised Domain Adaptation
  • Neural Networks
  • Natural Language Processing
  • Domain Shift
  • Out-of-Distribution Generalization

Fingerprint

Dive into the research topics of 'Neural Unsupervised Domain Adaptation in NLP—A Survey'. Together they form a unique fingerprint.

Cite this