A Comparative Analysis of Unsupervised Language Adaptation Methods

To overcome the lack of annotated resources in less-resourced languages, recent approaches have been proposed to perform unsupervised language adaptation. In this paper, we explore three recent proposals: Adversarial Training, Sentence Encoder Alignment and Shared-Private Architecture. We highlight the differences of these approaches in terms of unlabeled data requirements and capability to overcome additional domain shift in the data. A comparative analysis in two different tasks is conducted, namely on Sentiment Classification and Natural Language Inference. We show that adversarial training methods are more suitable when the source and target language datasets contain other variations in content besides the language shift. Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores.