Deep learning techniques have recently shown to be successful in many natural language processing tasks forming state-of-the-art systems. They require, however, a large amount of annotated data which is often missing. This paper explores the use of domain-adversarial learning as a regularizer to avoid overfitting when training domain invariant features for deep, complex neural networks in low-resource and zero-resource settings in new target domains or languages. In case of new languages, we show that monolingual word vectors can be directly used for training without prealignment. Their projection into a common space can be learnt ad-hoc at training time reaching the final performance of pretrained multilingual word vectors.
@article{arxiv.1807.05195,
title = {Low-Resource Text Classification using Domain-Adversarial Learning},
author = {Daniel Grießhaber and Ngoc Thang Vu and Johannes Maucher},
journal= {arXiv preprint arXiv:1807.05195},
year = {2020}
}