Translating in real-time, aka simultaneous translation, outputs translation words before the
input sentence ends, which is a challenging problem for conventional machine translation …

We investigate the potential of attention-based neural machine translation in simultaneous
translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding …

We address the problem of simultaneous translation by modifying the Neural MT decoder to
operate with dynamically built encoder and attention. We propose a tunable agent which …

Simultaneous machine translation consists in starting output generation before the entire
input sequence is available. Wait-k decoders offer a simple but efficient approach for this …

Simultaneous translation is widely useful but remains challenging. Previous work falls into
two main categories:(a) fixed-latency policies such as Ma et al.(2019) and (b) adaptive …

Decoder-only large language models (LLMs) have recently demonstrated impressive
capabilities in text generation and reasoning. Nonetheless, they have limited applications in …

Adaptive policies are better than fixed policies for simultaneous translation, since they can
flexibly balance the tradeoff between translation quality and latency based on the current …

Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP.
Previous work either uses fixed-latency policies, or train a complicated two-staged model …

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

Simultaneous speech translation aims to maintain translation quality while minimizing the
delay between reading input and incrementally producing the output. We propose a new …