This paper deals with cross-lingual sentiment analysis in Czech, English and French languages. We perform zero-shot cross-lingual classification using five linear transformations combined with LSTM and CNN based classifiers. We compare the performance of the individual transformations, and in addition, we confront the transformation-based approach with existing state-of-the-art BERT-like models. We show that the pre-trained embeddings from the target domain are crucial to improving the cross-lingual classification results, unlike in the monolingual classification, where the effect is not so distinctive.
@article{arxiv.2209.07244,
title = {Linear Transformations for Cross-lingual Sentiment Analysis},
author = {Pavel Přibáň and Jakub Šmíd and Adam Mištera and Pavel Král},
journal= {arXiv preprint arXiv:2209.07244},
year = {2022}
}