Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters

• URL: http://arxiv.org/abs/2407.13469v1
• Date: Thu, 18 Jul 2024 12:42:45 GMT
• Title: Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters
• Authors: Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis,
• Abstract summary: 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.
• Score: 5.312303275762104
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input, which poses challenges in terms of balancing quality and latency of the translation. The wait-$k$ policy offers a solution by starting to translate after consuming $k$ words, where the choice of the number $k$ directly affects the latency and quality. In applications where we seek to keep the choice over latency and quality at inference, the wait-$k$ policy obliges us to train more than one model. In this paper, we address the challenge of building one model that can fulfil multiple latency levels and we achieve this by introducing lightweight adapter modules into the decoder. The adapters are trained to be specialized for different wait-$k$ values and compared to other techniques they offer more flexibility to allow for reaping the benefits of parameter sharing and minimizing interference. Additionally, we show that by combining with an adaptive strategy, we can further improve the results. Experiments on two language directions show that our method outperforms or competes with other strong baselines on most latency values.

Related papers

• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• Adaptive Policy with Wait-$k$ Model for Simultaneous Translation [20.45004823667775]
  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-$k$ policy coupled with a standalone wait-$k$ translation model, or an adaptive policy jointly trained with the translation model. We propose a more flexible approach by decoupling the adaptive policy model from the translation model.
  arXiv  Detail & Related papers  (2023-10-23T12:16:32Z)
• Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff [49.75167556773752]
  Blockwise self-attentional encoder models have emerged as one promising end-to-end approach to simultaneous speech translation. We propose a modified incremental blockwise beam search incorporating local agreement or hold-$n$ policies for quality-latency control.
  arXiv  Detail & Related papers  (2023-09-20T14:59:06Z)
• 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)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• Data-Driven Adaptive Simultaneous Machine Translation [51.01779863078624]
  We propose a novel and efficient training scheme for adaptive SimulMT. Our method outperforms all strong baselines in terms of translation quality and latency.
  arXiv  Detail & Related papers  (2022-04-27T02:40:21Z)
• Does Simultaneous Speech Translation need Simultaneous Models? [17.305879157385675]
  We show that a single model trained offline can effectively serve not only offline but also simultaneous tasks at different latency regimes. This single-model solution does not only facilitate the adoption of well-established offline techniques and architectures without affecting latency but also yields similar or even better translation quality compared to the same model trained in the simultaneous setting.
  arXiv  Detail & Related papers  (2022-04-08T00:10:46Z)
• 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)
• Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy [6.487736084189248]
  Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence. Previous methods usually need to train multiple SiMT models for different latency levels, resulting in large computational costs. We propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency.
  arXiv  Detail & Related papers  (2021-09-11T09:43:15Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.