Search Results for author: Ulrich Germann

Found 22 papers, 3 papers with code

The University of Edinburgh’s submission to the German-to-English and English-to-German Tracks in the WMT 2020 News Translation and Zero-shot Translation Robustness Tasks

no code implementations WMT (EMNLP) 2020 Ulrich Germann

This paper describes the University of Edinburgh’s submission of German <-> English systems to the WMT2020 Shared Tasks on News Translation and Zero-shot Robustness.

Translation

Character Mapping and Ad-hoc Adaptation: Edinburgh's IWSLT 2020 Open Domain Translation System

1 code implementation WS 2020 Pin-zhen Chen, Nikolay Bogoychev, Ulrich Germann

This paper describes the University of Edinburgh{'}s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese$\leftrightarrow$Chinese translation task.

Machine Translation Translation

The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring

no code implementations ACL 2018 Ulrich Germann, Ren{\=a}rs Liepins, Guntis Barzdins, Didzis Gosko, Mir, Sebasti{\~a}o a, David Nogueira

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes.

Clustering Document Summarization +2

Integrating Multiple NLP Technologies into an Open-source Platform for Multilingual Media Monitoring

no code implementations WS 2018 Ulrich Germann, Ren{\=a}rs Liepins, Didzis Gosko, Guntis Barzdins

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes.

Automatic Speech Recognition (ASR) Machine Translation

Marian: Fast Neural Machine Translation in C++

2 code implementations ACL 2018 Marcin Junczys-Dowmunt, Roman Grundkiewicz, Tomasz Dwojak, Hieu Hoang, Kenneth Heafield, Tom Neckermann, Frank Seide, Ulrich Germann, Alham Fikri Aji, Nikolay Bogoychev, André F. T. Martins, Alexandra Birch

We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.

Machine Translation Translation

Regularization techniques for fine-tuning in neural machine translation

no code implementations EMNLP 2017 Antonio Valerio Miceli Barone, Barry Haddow, Ulrich Germann, Rico Sennrich

We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset.

Domain Adaptation L2 Regularization +4

Bilingual Document Alignment with Latent Semantic Indexing

no code implementations WS 2016 Ulrich Germann

We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16.

Cannot find the paper you are looking for? You can Submit a new open access paper.