Simultaneous translation, which translates sentences before they are finished, is useful in
many scenarios but is notoriously difficult due to word-order differences. While the …

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 (ST) starts translations synchronously while reading source
sentences, and is used in many online scenarios. The previous wait-k policy is concise and …

Computational approaches to simultaneous interpretation are stymied by how little we know
about the tactics human interpreters use. We produce a parallel corpus of translated and …

Incremental processing allows interactive systems to respond based on partial inputs, which
is a desirable property eg in dialogue agents. The currently popular Transformer architecture …

Beam search is universally used in full-sentence translation but its application to
simultaneous translation remains non-trivial, where output words are committed on the fly. In …

While humans process language incrementally, the best language encoders currently used
in NLP do not. Both bidirectional LSTMs and Transformers assume that the sequence that is …

Simultaneous translation is a task that requires starting translation before the speaker has
finished speaking, so we face a trade-off between latency and accuracy. In this work, we …

Simultaneous interpretation, the translation of speech from one language to another in real-
time, is an inherently difficult and strenuous task. One of the greatest challenges faced by …

A naive application of state-of-the-art bidirectional encoders for streaming sequence tagging
would require encoding each token from scratch for each new token in an incremental …