Are the Multilingual Models Better? Improving Czech Sentiment with Transformers
This work addresses sentiment analysis for the Czech language, demonstrating incremental improvements in model performance and cross-lingual transfer capabilities.
The paper tackled improving Czech sentiment analysis by comparing multilingual and monolingual transformer models, achieving new state-of-the-art results on three datasets and showing that multilingual models can perform zero-shot cross-lingual classification with performance within 4.4% of monolingual models.
In this paper, we aim at improving Czech sentiment with transformer-based models and their multilingual versions. More concretely, we study the task of polarity detection for the Czech language on three sentiment polarity datasets. We fine-tune and perform experiments with five multilingual and three monolingual models. We compare the monolingual and multilingual models' performance, including comparison with the older approach based on recurrent neural networks. Furthermore, we test the multilingual models and their ability to transfer knowledge from English to Czech (and vice versa) with zero-shot cross-lingual classification. Our experiments show that the huge multilingual models can overcome the performance of the monolingual models. They are also able to detect polarity in another language without any training data, with performance not worse than 4.4 % compared to state-of-the-art monolingual trained models. Moreover, we achieved new state-of-the-art results on all three datasets.