Neural Machine Translation
Module Description
| Course | Module Abbreviation | Credit Points |
|---|---|---|
| BA-2010 | AS-CL | 8 LP |
| Master | SS-CL, SS-TAC | 8 LP |
| Seminar Informatik | BA + MA | 4 LP |
| Anwendungsgebiet Informatik | MA | 8 LP |
| Anwendungsgebiet SciComp | MA | 8 LP |
| Lecturer | Stefan Riezler |
| Module Type | |
| Language | English |
| First Session | 21.04.2022 |
| Time and Place |
Donnerstag, 10:15–11:45 INF 328 / SR25 |
| Commitment Period | tbd. |
Prerequisite for Participation
Good knowledge of statistical machine learning (e.g., by successful completion of courses "Statistical Methods for Computational Linguistics" and/or "Neural Networks: Architectures and Applications for NLP") and experience in experimental work (e.g., software project or seminar implementation project)
Assessment
Content
Neural machine translation -- the automatic translation of text or speech from one natural language into another -- has made a major qualitative leap in recent years, enabling the transition from machine translation as an AI-complete problem to a commodity tool that is widely used by industry and private persons. The goal of this seminar is to gain a thorough understanding of this success story by investigating the central building blocks of neural machine translation, including - neural encoder-decoder architectures for translation, - input encodings, - training methods, - decoding paradigms, - issues and methods for interpretability, and other topics.
