Grunddaten
| Titel | Explainable Machine Translation |
| Beschreibung | The aim of the project is to investigate how explainable NMT methods are. For example, attention weights from the Transformer architecture can be used as alignments, however it is not straight-forward which weights can be used. Contact: Ray Kodali Relevant literature: |
| Heimateinrichtung | Department für Informatik |
| Art der Arbeit | konzeptuell / theoretisch |
| Abschlussarbeitstyp | Master |
| Autor | Ilira Troshani |
| Status | verfügbar |
| Aufgabenstellung | |
| Voraussetzung |
Programming in Python, Pytorch (or Tensorflow) |
| Erstellt | 14.04.2022 |
