Related papers: The NiuTrans System for WNGT 2020 Efficiency Task
Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…
In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…
With the recent developments in the field of Natural Language Processing, there has been a rise in the use of different architectures for Neural Machine Translation. Transformer architectures are used to achieve state-of-the-art accuracy,…
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…
We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…
We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent…
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph…
Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to…
There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a…
The deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is limited in computational resources such as mobile or edge…
In state-of-the-art Neural Machine Translation (NMT), an attention mechanism is used during decoding to enhance the translation. At every step, the decoder uses this mechanism to focus on different parts of the source sentence to gather the…
In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from…
Transformer-based approaches have been successfully used to obtain state-of-the-art accuracy on natural language processing (NLP) tasks with semi-structured tables. These model architectures are typically deep, resulting in slow training…
This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…
We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words at each decoding time step so that the generation can be helped with the…
Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…
Recent works have proven the effectiveness of k-nearest-neighbor machine translation(a.k.a kNN-MT) approaches to produce remarkable improvement in cross-domain translations. However, these models suffer from heavy retrieve overhead on the…
8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently. On the other hand, previous systems still rely on 32-bit floating point for certain…
We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging…
In this paper we provide the largest published comparison of translation quality for phrase-based SMT and neural machine translation across 30 translation directions. For ten directions we also include hierarchical phrase-based MT.…