Future-Guided Incremental Transformer for Simultaneous Translation

2020-12-23 · Shaolei Zhang, Yang Feng, Liangyou Li

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 achieved good results in ST. However, wait-k policy faces two weaknesses: low training speed caused by the recalculation of hidden states and lack of future source information to guide training. For the low training speed, we propose an incremental Transformer with an average embedding layer (AEL) to accelerate the speed of calculation of the hidden states during training. For future-guided training, we propose a conventional Transformer as the teacher of the incremental Transformer, and try to invisibly embed some future information in the model through knowledge distillation. We conducted experiments on Chinese-English and German-English simultaneous translation tasks and compared with the wait-k policy to evaluate the proposed method. Our method can effectively increase the training speed by about 28 times on average at different k and implicitly embed some predictive abilities in the model, achieving better translation quality than wait-k baseline.

📄 PDF Abstract BibTeX arXiv:2012.12465

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation Translation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

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…

Residual Connection 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

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 $x$…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Prediction Improves Simultaneous Neural Machine Translation

2018-10-01 · EMNLP 2018 10 · Ashkan Alinejad, Maryam Siahbani, Anoop Sarkar

Simultaneous speech translation aims to maintain translation quality while minimizing the delay between reading input and incrementally producing the output. We propose a new general-purpose prediction action which predi…

Machine Translation Prediction reinforcement-learning Reinforcement Learning+2

NAIST Simultaneous Speech Translation System for IWSLT 2024

2024-06-30 · Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano 외

This paper describes NAIST's submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-{German, Japanese, Chinese} speech-to-text translation and English-to-Japanese speech-to-speech translat…

Speech-to-Speech Translation Speech-to-Text Speech-to-Text Translation text-to-speech+2

Anticipating Future with Large Language Model for Simultaneous Machine Translation

2024-10-29 · Siqi Ouyang, Oleksii Hrinchuk, Zhehuai Chen, Vitaly Lavrukhin 외

Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods only use the partial utterance that has already arrived at the input and the generated …

Language Modeling Language Modelling Large Language Model Machine Translation+1

Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation

2019-12-06 · Naveen Arivazhagan, Colin Cherry, Te I, Wolfgang Macherey 외

We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a live audio feed, such as a lecture or play-…

Form Machine Translation speech-recognition Speech Recognition+2

From Simultaneous to Streaming Machine Translation by Leveraging Streaming History

2022-03-04 · ACL 2022 5 · Javier Iranzo-Sánchez, Jorge Civera, Alfons Juan

Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of t…

Machine Translation Sentence Translation