Transllama: Llm-based simultaneous translation system

R Koshkin, K Sudoh, S Nakamura - arxiv preprint arxiv:2402.04636, 2024 - arxiv.org
Decoder-only large language models (LLMs) have recently demonstrated impressive
capabilities in text generation and reasoning. Nonetheless, they have limited applications in …

Unified segment-to-segment framework for simultaneous sequence generation

S Zhang, Y Feng - Advances in Neural Information …, 2023 - 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 …

Sillm: Large language models for simultaneous machine translation

S Guo, S Zhang, Z Ma, M Zhang, Y Feng - arxiv preprint arxiv:2402.13036, 2024 - arxiv.org
Simultaneous Machine Translation (SiMT) generates translations while reading the source
sentence, necessitating a policy to determine the optimal timing for reading and generating …

Dap-SiMT: divergence-based adaptive policy for simultaneous machine translation

L Zhao, Z Zeng - International Journal of Machine Learning and …, 2024 - Springer
In the realm of Simultaneous Machine Translation (SiMT), a robust read/write (R/W) policy is
essential alongside a high-quality translation model. Traditional methods typically employ …

Simultaneous machine translation with tailored reference

S Guo, S Zhang, Y Feng - arxiv preprint arxiv:2310.13588, 2023 - arxiv.org
Simultaneous machine translation (SiMT) generates translation while reading the whole
source sentence. However, existing SiMT models are typically trained using the same …

Adaptive Policy with Wait- Model for Simultaneous Translation

L Zhao, K Fan, W Luo, J Wu, S Wang, Z Zeng… - arxiv preprint arxiv …, 2023 - arxiv.org
Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction
with a high-quality translation model. Traditional methods rely on either a fixed wait-$ k …

Glancing future for simultaneous machine translation

S Guo, S Zhang, Y Feng - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Simultaneous machine translation (SiMT) outputs translation while reading the source
sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT …

Decoder-only streaming transformer for simultaneous translation

S Guo, S Zhang, Y Feng - arxiv preprint arxiv:2406.03878, 2024 - arxiv.org
Simultaneous Machine Translation (SiMT) generates translation while reading source
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

S Guo, S Zhang, Z Ma, M Zhang, Y Feng - arxiv preprint arxiv:2406.06910, 2024 - arxiv.org
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 …

Enhanced simultaneous machine translation with word-level policies

K Kim, H Cho - arxiv preprint arxiv:2310.16417, 2023 - arxiv.org
Recent years have seen remarkable advances in the field of Simultaneous Machine
Translation (SiMT) due to the introduction of innovative policies that dictate whether to READ …