Unified segment-to-segment framework for simultaneous sequence generation
S Zhang, Y Feng - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …
Glancing future for simultaneous machine translation
Simultaneous machine translation (SiMT) outputs translation while reading the source
sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT …
sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT …
SimulPL: Aligning Human Preferences in Simultaneous Machine Translation
Simultaneous Machine Translation (SiMT) generates translations while receiving streaming
source inputs. This requires the SiMT model to learn a read/write policy, deciding when to …
source inputs. This requires the SiMT model to learn a read/write policy, deciding when to …
Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
Simultaneous generation models write generation results while reading streaming inputs,
necessitating a policy-maker to determine the appropriate output timing. Existing …
necessitating a policy-maker to determine the appropriate output timing. Existing …
Decoder-only Streaming Transformer for Simultaneous Translation
Simultaneous Machine Translation (SiMT) generates translation while reading source
tokens, essentially producing the target prefix based on the source prefix. To achieve good …
tokens, essentially producing the target prefix based on the source prefix. To achieve good …
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
Simultaneous Machine Translation (SiMT) generates target translations while reading the
source sentence. It relies on a policy to determine the optimal timing for reading sentences …
source sentence. It relies on a policy to determine the optimal timing for reading sentences …
PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation
L Zhao, J Li, Z Zeng - arxiv preprint arxiv:2410.04075, 2024 - arxiv.org
Simultaneous Machine Translation (SiMT) requires target tokens to be generated in real-
time as streaming source tokens are consumed. Traditional approaches to SiMT typically …
time as streaming source tokens are consumed. Traditional approaches to SiMT typically …