English
Related papers

Related papers: DePA: Improving Non-autoregressive Machine Transla…

200 papers

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because the decoder predicts text tokens (such as characters or words) in an autoregressive manner, it is difficult for an AED…

Computation and Language · Computer Science 2021-08-31 Ye Bai , Jiangyan Yi , Jianhua Tao , Zhengkun Tian , Zhengqi Wen , Shuai Zhang

Non-autoregressive translation (NAT) model achieves a much faster inference speed than the autoregressive translation (AT) model because it can simultaneously predict all tokens during inference. However, its translation quality suffers…

Computation and Language · Computer Science 2023-01-30 Huanran Zheng , Wei Zhu , Pengfei Wang , Xiaoling Wang

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…

Computation and Language · Computer Science 2018-05-31 Jean-Benoit Delbrouck , Stéphane Dupont

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…

Neural and Evolutionary Computing · Computer Science 2019-08-06 Albert Zeyer , Tamer Alkhouli , Hermann Ney

Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…

Computation and Language · Computer Science 2021-09-13 Weizhi Wang , Zhirui Zhang , Yichao Du , Boxing Chen , Jun Xie , Weihua Luo

Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if…

Computation and Language · Computer Science 2018-12-27 Xinwei Geng , Longyue Wang , Xing Wang , Bing Qin , Ting Liu , Zhaopeng Tu

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Leheng Zhang , Wei Long , Yawei Li , Xingyu Zhou , Xiaorui Zhao , Shuhang Gu

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

Neural and Evolutionary Computing · Computer Science 2018-06-04 Shuai Tang , Hailin Jin , Chen Fang , Zhaowen Wang , Virginia R. de Sa

Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Wenchi Ma , Tianxiao Zhang , Guanghui Wang

Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and…

Information Retrieval · Computer Science 2024-04-23 Guangyuan Ma , Xing Wu , Zijia Lin , Songlin Hu

Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…

Computation and Language · Computer Science 2023-10-20 Yi Bin , Wenhao Shi , Bin Ji , Jipeng Zhang , Yujuan Ding , Yang Yang

Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations…

Computation and Language · Computer Science 2024-07-12 Christian Tomani , David Vilar , Markus Freitag , Colin Cherry , Subhajit Naskar , Mara Finkelstein , Xavier Garcia , Daniel Cremers

Neural machine translation (NMT) typically adopts the encoder-decoder framework. A good understanding of the characteristics and functionalities of the encoder and decoder can help to explain the pros and cons of the framework, and design…

Computation and Language · Computer Science 2019-08-20 Tianyu He , Xu Tan , Tao Qin

Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Yang Liu , Chen Chen , Can Wang , Xulin King , Mengyuan Liu

Humans possess a versatile mechanism for extracting structured representations of our visual world. When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them. To mimic…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Mingyu Ding , Yikang Shen , Lijie Fan , Zhenfang Chen , Zitian Chen , Ping Luo , Joshua B. Tenenbaum , Chuang Gan

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Han Qiu , Jiaxing Huang , Peng Gao , Lewei Lu , Xiaoqin Zhang , Shijian Lu

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

Computation and Language · Computer Science 2017-12-07 Jinbae Im , Sungzoon Cho

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear…

Computation and Language · Computer Science 2026-04-16 Vishal Pramanik , Maisha Maliha , Nathaniel D. Bastian , Sumit Kumar Jha

Machine Translation (MT) is a zone of concentrate in Natural Language processing which manages the programmed interpretation of human language, starting with one language then onto the next by the PC. Having a rich research history…

Computation and Language · Computer Science 2019-09-24 Siddhant Srivastava , Ritu Tiwari