Information-transport-based policy for simultaneous translation
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 …
hence requires a policy to determine whether to translate a target token or wait for the next …
Better simultaneous translation with monotonic knowledge distillation
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 …
generating target tokens before the source sentence is fully consumed. This can lead to the …
Learning adaptive segmentation policy for simultaneous translation
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 …
achieve high accuracy, the model usually needs to wait for more streaming text before …
Unified segment-to-segment framework for simultaneous sequence generation
Simultaneous sequence generation is a pivotal task for real-time scenarios, such as
streaming speech recognition, simultaneous machine translation and simultaneous speech …
streaming speech recognition, simultaneous machine translation and simultaneous speech …
Non-autoregressive streaming transformer for simultaneous translation
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 …
latency and translation quality. However, training these models to achieve high quality while …
RealTranS: End-to-end simultaneous speech translation with convolutional weighted-shrinking transformer
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 …
language into text in another language in real-time, is useful in many scenarios but has not …
Attention as a guide for simultaneous speech translation
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 …
modeling and machine translation. Although its patterns have been exploited to perform …
Wait-info policy: Balancing source and target at information level for simultaneous machine translation
Simultaneous machine translation (SiMT) outputs the translation while receiving the source
inputs, and hence needs to balance the received source information and translated target …
inputs, and hence needs to balance the received source information and translated target …
Improving simultaneous machine translation with monolingual data
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge
distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However …
distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However …
Hidden markov transformer for simultaneous machine translation
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 …
source sequence, and hence learning when to start translating each target token is the core …