10.18419/darus-1849Munz, TanjaTanjaMunz0000-0003-3960-3290University of StuttgartVäth, DirkDirkVäthUniversity of StuttgartKuznecov, PaulPaulKuznecovUniversity of StuttgartVu, Ngoc ThangNgoc ThangVu1052005233University of StuttgartWeiskopf, DanielDanielWeiskopf0000-0003-1174-1026University of StuttgartNMTVis - Neural Machine Translation Visualization SystemDaRUS2021Computer and Information ScienceVisual AnalyticsNeural Machine TranslationMachine LearningTransformerLong short-term memoryBeam SearchAttentionMunz, TanjaTanjaMunzUniversity of Stuttgart2021-05-112021-05-2632868780application/zip1.0MIT LicenseNMTVis is a web-based visual analytics system to analyze, understand, and correct translations generated with neural machine translation. First, a document can be translated using a neural machine translation model (we support an LSTM-based and the Transformer architecture). Afterward, users can find mistranslated sentences, explore and correct these sentences and retrain the model to generate a better translation for the whole document. Our approach targets the correction of domain-specific documents.You may find the most recent version of the source code on GitHub: <a href="https://github.com/MunzT/NMTVis">https://github.com/MunzT/NMTVis</a> <br> Trained models for translation from German to English and vice versa can be found here: <a href="https://doi.org/10.18419/darus-1850">https://doi.org/10.18419/darus-1850</a>Deutsche ForschungsgemeinschaftEXC 2075 - 390740016