265 citations · 1.1k across the 50 of their papers we have counts for
7 papers · 1 filter
Improving Zero-Shot Translation by Disentangling Positional Information
Danni Liu, Jan Niehues, James Cross +2
Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being concep…
The Large Hadron-Electron Collider at the HL-LHC
P. Agostini, H. Aksakal, S. Alekhin +333
The Large Hadron electron Collider (LHeC) is designed to move the field of deep inelastic scattering (DIS) to the energy and intensity frontier of particle physics. Exploiting ener…
Adapting End-to-End Speech Recognition for Readable Subtitles
Danni Liu, Jan Niehues, Gerasimos Spanakis
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce out…
Relative Positional Encoding for Speech Recognition and Direct Translation
Ngoc-Quan Pham, Thanh-Le Ha, Tuan-Nam Nguyen +5
Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for…
Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
Danni Liu, Gerasimos Spanakis, Jan Niehues
Encoder-decoder models provide a generic architecture for sequence-to-sequence tasks such as speech recognition and translation. While offline systems are often evaluated on qualit…
Machine Translation with Unsupervised Length-Constraints
Jan Niehues
We have seen significant improvements in machine translation due to the usage of deep learning. While the improvements in translation quality are impressive, the encoder-decoder ar…
Low Latency ASR for Simultaneous Speech Translation
Thai Son Nguyen, Jan Niehues, Eunah Cho +6
User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques f…