Related papers: Future-Guided Incremental Transformer for Simultan…
Imitation learning methods have demonstrated considerable success in teaching autonomous systems complex tasks through expert demonstrations. However, a limitation of these methods is their lack of interpretability, particularly in…
The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of…
Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables…
Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…
The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the…
Simultaneous machine translation (SiMT) outputs translation while reading source sentence and hence requires a policy to decide whether to wait for the next source word (READ) or generate a target word (WRITE), the actions of which form a…
Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently…
Reinforcement learning (RL) is frequently used to increase performance in text generation tasks, including machine translation (MT), notably through the use of Minimum Risk Training (MRT) and Generative Adversarial Networks (GAN). However,…
In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…
Simultaneous Speech Translation (SimulST) systems stream in audio while simultaneously emitting translated text or speech. Such systems face the significant challenge of balancing translation quality and latency. We introduce a strategy to…
With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point of research. Despite the commendable performance of general models such as the Transformer in various…
Language models often show little to no improvement (i.e., "saturation") when trained via vanilla supervised fine-tuning (SFT) on data similar to what they saw in their training set (e.g., MATH). We introduce a new fine-tuning strategy,…
Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which…
Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked…
Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation…
Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…
While contrastive learning greatly advances the representation of sentence embeddings, it is still limited by the size of the existing sentence datasets. In this paper, we present TransAug (Translate as Augmentation), which provide the…
Simultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation accuracy and latency. We have to determine when we start…
This paper describes the FBK's participation in the Simultaneous Translation and Automatic Subtitling tracks of the IWSLT 2023 Evaluation Campaign. Our submission focused on the use of direct architectures to perform both tasks: for the…
Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…