Linear Transformations for Cross-lingual Sentiment Analysis
This work addresses sentiment analysis across languages, but it is incremental as it compares existing transformations and models without introducing major innovations.
The paper tackled cross-lingual sentiment analysis by evaluating linear transformations with LSTM and CNN classifiers in Czech, English, and French, showing that pre-trained embeddings from the target domain significantly improve cross-lingual classification results, unlike in monolingual settings.
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.