paper-with-me

홈 › Papers

Decoder-only Streaming Transformer for Simultaneous Translation

2024-06-06 · Shoutao Guo, Shaolei Zhang, Yang Feng

Simultaneous Machine Translation (SiMT) generates translation while reading source tokens, essentially producing the target prefix based on the source prefix. To achieve good performance, it leverages the relationship between source and target prefixes to exact a policy to guide the generation of translations. Although existing SiMT methods primarily focus on the Encoder-Decoder architecture, we explore the potential of Decoder-only architecture, owing to its superior performance in various tasks and its inherent compatibility with SiMT. However, directly applying the Decoder-only architecture to SiMT poses challenges in terms of training and inference. To alleviate the above problems, we propose the first Decoder-only SiMT model, named Decoder-only Streaming Transformer (DST). Specifically, DST separately encodes the positions of the source and target prefixes, ensuring that the position of the target prefix remains unaffected by the expansion of the source prefix. Furthermore, we propose a Streaming Self-Attention (SSA) mechanism tailored for the Decoder-only architecture. It is capable of obtaining translation policy by assessing the sufficiency of input source information and integrating with the soft-attention mechanism to generate translations. Experiments demonstrate that our approach achieves state-of-the-art performance on three translation tasks.

📄 PDF Abstract BibTeX arXiv:2406.03878

Code (1)

ictnlp/DST 공식 구현 pytorch

Tasks

DecoderMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Focus 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs

2026-05-29 · Sara Papi, Luisa Bentivogli arxiv

Simultaneous speech-to-text translation (SimulST) generates translations while speech is still unfolding, requiring a streaming policy that decides when to read and when to write. State-of-the-art approaches rely on atte…

Speech-to-Text Translation

Non-autoregressive Streaming Transformer for Simultaneous Translation

2023-10-23 · Zhengrui Ma, Shaolei Zhang, Shoutao Guo, Chenze Shao 외

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 maintaining low latency often leads to …

DecoderMachine TranslationTranslation

Streaming Simultaneous Speech Translation with Augmented Memory Transformer

2020-10-30 · Xutai Ma, Yongqiang Wang, Mohammad Javad Dousti, Philipp Koehn 외

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an en…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation

2022-04-19 · Keqi Deng, Shinji Watanabe, Jiatong Shi, Siddhant Arora

Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is stil…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+2

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR

2021-06-11 · Findings (ACL) 2021 8 · Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra la…

Simultaneous Speech-to-Text TranslationSpeech-to-TextSpeech-to-Text TranslationTranslation