Self-Modifying State Modeling for Simultaneous Machine Translation

• URL: http://arxiv.org/abs/2406.02237v1
• Date: Tue, 4 Jun 2024 11:57:58 GMT
• Title: Self-Modifying State Modeling for Simultaneous Machine Translation
• Authors: Donglei Yu, Xiaomian Kang, Yuchen Liu, Yu Zhou, Chengqing Zong,
• Abstract summary: Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs. Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations. We propose textbfSelf-textbfModifying textbfState textbfModeling (SM$2$), a novel training paradigm for SiMT task.
• Score: 25.11963998838586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a \textit{decision path}. Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations. These methods not only fail to precisely optimize the policy due to the inability to accurately assess the individual impact of each decision on SiMT performance, but also cannot sufficiently explore all potential paths because of their vast number. Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models. To solve these issues, we propose \textbf{S}elf-\textbf{M}odifying \textbf{S}tate \textbf{M}odeling (SM$^2$), a novel training paradigm for SiMT task. Without building decision paths, SM$^2$ individually optimizes decisions at each state during training. To precisely optimize the policy, SM$^2$ introduces Self-Modifying process to independently assess and adjust decisions at each state. For sufficient exploration, SM$^2$ proposes Prefix Sampling to efficiently traverse all potential states. Moreover, SM$^2$ ensures compatibility with bidirectional encoders, thus achieving higher translation quality. Experiments show that SM$^2$ outperforms strong baselines. Furthermore, SM$^2$ allows offline machine translation models to acquire SiMT ability with fine-tuning.

Related papers

• Aligning Large Language Models via Self-Steering Optimization [78.42826116686435]
  We introduce Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality preference signals. $SSO$ maintains the accuracy of signals by ensuring a consistent gap between chosen and rejected responses. We validate the effectiveness of $SSO$ with two foundation models, Qwen2 and Llama3.1, indicating that it provides accurate, on-policy preference signals.
  arXiv  Detail & Related papers  (2024-10-22T16:04:03Z)
• PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation [8.1299957975257]
  Simultaneous Machine Translation (SiMT) requires target tokens to be generated in real-time as streaming source tokens are consumed. We propose PsFuture, the first zero-shot adaptive read/write policy for SiMT. We introduce a novel training strategy, Prefix-to-Full (P2F), specifically tailored to adjust offline translation models for SiMT applications.
  arXiv  Detail & Related papers  (2024-10-05T08:06:33Z)
• Metareasoning in uncertain environments: a meta-BAMDP framework [1.0923877073891441]
  This paper proposes a meta Bayes-Adaptive MDP framework to handle metareasoning in environments with unknown reward/transition distributions. As a first step, we apply the framework to two-armed Bernoulli bandit (TABB) tasks, which have often been used to study human decision making.
  arXiv  Detail & Related papers  (2024-08-02T13:15:01Z)
• Towards Zero-Shot Multimodal Machine Translation [64.9141931372384]
  We propose a method to bypass the need for fully supervised data to train multimodal machine translation systems. Our method, called ZeroMMT, consists in adapting a strong text-only machine translation (MT) model by training it on a mixture of two objectives. To prove that our method generalizes to languages with no fully supervised training data available, we extend the CoMMuTE evaluation dataset to three new languages: Arabic, Russian and Chinese.
  arXiv  Detail & Related papers  (2024-07-18T15:20:31Z)
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning [54.682106515794864]
  offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. This paper introduces $textbfLanguage Models for $textbfMo$tion Control ($textbfLaMo$), a general framework based on Decision Transformers to use pre-trained Language Models (LMs) for offline RL. Empirical results indicate $textbfLaMo$ achieves state-of-the-art performance in sparse-reward tasks.
  arXiv  Detail & Related papers  (2023-10-31T16:24:17Z)
• 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)
• Modeling Dual Read/Write Paths for Simultaneous Machine Translation [21.03142288187605]
  We propose a method of Dual Path SiMT which introduces duality constraints to guide the read/write path. Experiments on En-Vi and De-En SiMT tasks show that our method can outperform strong baselines under all latency.
  arXiv  Detail & Related papers  (2022-03-17T08:35:36Z)
• 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)
• Exploring Unsupervised Pretraining Objectives for Machine Translation [99.5441395624651]
  Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT) Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. We compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context.
  arXiv  Detail & Related papers  (2021-06-10T10:18:23Z)
• Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games [102.23975166536326]
  Tree-form sequential decision making (TFSDM) extends classical one-shot decision making by modeling tree-form interactions between an agent and a potentially adversarial environment. It captures the online decision-making problems that each player faces in an extensive-form game, as well as Markov decision processes and partially-observable Markov decision processes where the agent conditions on observed history. In this paper, we give the first algorithm for the bandit linear optimization problem for dilatedDM that offers both (i) linear-time losses and (ii) $O(sqrtT)$ cumulative regret in
  arXiv  Detail & Related papers  (2021-03-08T05:00:13Z)

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.