Debugging Translations of Transformer-based Neural Machine Translation Systems
Matīss Rikters, Mārcis Pinnis · Baltic Journal of Modern Computing · 2018
In this paper, we describe a tool for debugging the output and attention weights of neural machine translation (NMT) systems and for improved estimations of confidence about the output based on the attention.We dive deeper into ways for it to handle output from transformerbased NMT models.Its purpose is to help researchers and developers find weak and faulty translations that their NMT systems produce without the need for reference translations.We present a demonstration website of our tool with examples of good and bad translations: http: //attention.lielakeda.lv.