Publication at Faculty of Mathematics and Physics |
2018
Abstract
In this work, we focus on three different NLP tasks: image captioning, machine translation, and sentiment analysis. We reimplement successful approaches of other authors and adapt them to the Czech language.
We provide end-to-end architectures that achieve state-of-the-art or nearly state-of-the-art results on all of the tasks within a single sequence learning toolkit. The trained models are available both for download as well as in an online demo.