Debugging Neural Machine Translations
This tool addresses debugging challenges for researchers and developers working on neural machine translation, but it is incremental as it builds on existing attention-based methods without introducing new paradigms.
The paper tackles the problem of debugging neural machine translation systems by developing a tool that helps researchers and developers identify weak or faulty translations without needing reference translations, and it includes features for comparing outputs from different NMT engines.
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. The purpose of the tool is to help researchers and developers find weak and faulty example translations that their NMT systems produce without the need for reference translations. Our tool also includes an option to directly compare translation outputs from two different NMT engines or experiments. In addition, we present a demo website of our tool with examples of good and bad translations: http://attention.lielakeda.lv