Related papers: Guiding Teacher Forcing with Seer Forcing for Neur…
Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach,…
Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In…
Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…
Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training.…
Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the…
Knowledge distillation is a technique used to train a small student network using the output generated by a large teacher network, and has many empirical advantages~\citep{Hinton2015DistillingTK}. While the standard one-shot approach to…
Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to the target representations. In…
The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright…
Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new tasks and deploying…
Conventional transfer learning leverages weights of pre-trained networks, but mandates the need for similar neural architectures. Alternatively, knowledge distillation can transfer knowledge between heterogeneous networks but often requires…
Machine translation systems require semantic knowledge and grammatical understanding. Neural machine translation (NMT) systems often assume this information is captured by an attention mechanism and a decoder that ensures fluency. Recent…
Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based…
Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned…
Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the…
The task of translating between programming languages differs from the challenge of translating natural languages in that programming languages are designed with a far more rigid set of structural and grammatical rules. Previous work has…
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because…
We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language…