Related papers: Data-Driven Adaptive Simultaneous Machine Translation

Data-Driven Adaptive Simultaneous Machine Translation

URL: http://arxiv.org/abs/2204.12672v1
Date: Wed, 27 Apr 2022 02:40:21 GMT
Title: Data-Driven Adaptive Simultaneous Machine Translation
Authors: Guangxu Xun, Mingbo Ma, Yuchen Bian, Xingyu Cai, Jiaji Huang, Renjie Zheng, Junkun Chen, Jiahong Yuan, Kenneth Church, Liang Huang
Abstract summary: We propose a novel and efficient training scheme for adaptive SimulMT. Our method outperforms all strong baselines in terms of translation quality and latency.
Score: 51.01779863078624
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major limitations: (a) it is a fixed policy that can not adaptively adjust latency given context, and (b) its training is much slower than full-sentence translation. To alleviate these issues, we propose a novel and efficient training scheme for adaptive SimulMT by augmenting the training corpus with adaptive prefix-to-prefix pairs, while the training complexity remains the same as that of training full-sentence translation models. Experiments on two language pairs show that our method outperforms all strong baselines in terms of translation quality and latency.

Related papers

Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters [5.312303275762104]
Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input. wait-$k$ policy offers a solution by starting to translate after consuming $k$ words. In this paper, we address the challenge of building one model that can fulfil multiple latency levels.
arXiv Detail & Related papers (2024-07-18T12:42:45Z)
LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation [6.411228564798412]
Simultaneous machine translation is useful in many live scenarios but very challenging due to the trade-off between accuracy and latency. We propose a novel adaptive training policy called LEAPT, which allows our machine translation model to learn how to translate source prefixes and make use of the future context.
arXiv Detail & Related papers (2023-03-21T11:17:37Z)
Non-Parametric Domain Adaptation for End-to-End Speech Translation [72.37869362559212]
End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. We propose a novel non-parametric method that leverages domain-specific text translation corpus to achieve domain adaptation for the E2E-ST system.
arXiv Detail & Related papers (2022-05-23T11:41:02Z)
Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation [75.86581380817464]
A SimulST system generally includes two components: the pre-decision that aggregates the speech information and the policy that decides to read or write. This paper proposes to model the adaptive policy by adapting the Continuous Integrate-and-Fire (CIF) Compared with monotonic multihead attention (MMA), our method has the advantage of simpler computation, superior quality at low latency, and better generalization to long utterances.
arXiv Detail & Related papers (2022-03-22T23:33:18Z)
Anticipation-free Training for Simultaneous Translation [70.85761141178597]
Simultaneous translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. Existing methods increase latency or introduce adaptive read-write policies for SimulMT models to handle local reordering and improve translation quality. We propose a new framework that decomposes the translation process into the monotonic translation step and the reordering step.
arXiv Detail & Related papers (2022-01-30T16:29:37Z)
DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
arXiv Detail & Related papers (2021-11-14T17:28:09Z)
Phrase-level Active Learning for Neural Machine Translation [107.28450614074002]
We propose an active learning setting where we can spend a given budget on translating in-domain data. We select both full sentences and individual phrases from unlabelled data in the new domain for routing to human translators. In a German-English translation task, our active learning approach achieves consistent improvements over uncertainty-based sentence selection methods.
arXiv Detail & Related papers (2021-06-21T19:20:42Z)
Future-Guided Incremental Transformer for Simultaneous Translation [6.8452940299620435]
Simultaneous translation (ST) starts synchronously while reading source sentences, and is used in many online scenarios. 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. We propose an incremental Transformer with an average embedding layer (AEL) to accelerate the speed of calculation of hidden states.
arXiv Detail & Related papers (2020-12-23T03:04:49Z)
Simultaneous Translation Policies: From Fixed to Adaptive [29.699912674525056]
We design an algorithm to achieve adaptive policies via a simple composition of a set of fixed policies. Our algorithm can outperform fixed ones by up to 4 BLEU points for the same latency. It even surpasses the BLEU score of full-sentence translation in the greedy mode.
arXiv Detail & Related papers (2020-04-27T20:56:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.