Simultaneous translation (ST) outputs translation while receiving the source inputs, and
hence requires a policy to determine whether to translate a target token or wait for the next …

Simultaneous machine translation (SiMT) presents a unique challenge as it requires
generating target tokens before the source sentence is fully consumed. This can lead to the …

Balancing accuracy and latency is a great challenge for simultaneous translation. To
achieve high accuracy, the model usually needs to wait for more streaming text before …

Simultaneous sequence generation is a pivotal task for real-time scenarios, such as
streaming speech recognition, simultaneous machine translation and simultaneous speech …

Simultaneous machine translation (SiMT) models are trained to strike a balance between
latency and translation quality. However, training these models to achieve high quality while …

End-to-end simultaneous speech translation (SST), which directly translates speech in one
language into text in another language in real-time, is useful in many scenarios but has not …

The study of the attention mechanism has sparked interest in many fields, such as language
modeling and machine translation. Although its patterns have been exploited to perform …

Simultaneous machine translation (SiMT) outputs the translation while receiving the source
inputs, and hence needs to balance the received source information and translated target …

Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge
distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However …

Simultaneous machine translation (SiMT) outputs the target sequence while receiving the
source sequence, and hence learning when to start translating each target token is the core …