English
Related papers

Related papers: Optimizing Non-Autoregressive Transformers with Co…

200 papers

Learning effective recommendation models from sparse user interactions represents a fundamental challenge in developing sequential recommendation methods. Recently, pre-training-based methods have been developed to tackle this challenge.…

Information Retrieval · Computer Science 2023-09-21 Bo Peng , Srinivasan Parthasarathy , Xia Ning

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge. In time series forecasting, the autoregressive…

Machine Learning · Computer Science 2021-06-01 Kai Chen , Guang Chen , Dan Xu , Lijun Zhang , Yuyao Huang , Alois Knoll

In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position,…

Computation and Language · Computer Science 2020-11-13 Xiang Kong , Zhisong Zhang , Eduard Hovy

Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence…

Computation and Language · Computer Science 2022-11-14 Xinyou Wang , Zaixiang Zheng , Shujian Huang

Autoregressive (AR) models have been the dominating approach to conditional sequence generation, but are suffering from the issue of high inference latency. Non-autoregressive (NAR) models have been recently proposed to reduce the latency…

Machine Learning · Computer Science 2020-07-01 Zhiqing Sun , Yiming Yang

Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve the efficiency of MNMT, but requires expensive knowledge…

Computation and Language · Computer Science 2025-02-10 Chenyang Huang , Fei Huang , Zaixiang Zheng , Osmar R. Zaïane , Hao Zhou , Lili Mou

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

Computation and Language · Computer Science 2021-12-30 Tong Zhang , Wei Ye , Baosong Yang , Long Zhang , Xingzhang Ren , Dayiheng Liu , Jinan Sun , Shikun Zhang , Haibo Zhang , Wen Zhao

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…

Computation and Language · Computer Science 2019-11-22 Raphael Shu , Jason Lee , Hideki Nakayama , Kyunghyun Cho

Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest in non-autoregressive (NAR) models, which promise faster…

Computation and Language · Computer Science 2022-05-05 Jindřich Helcl , Barry Haddow , Alexandra Birch

Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…

Computation and Language · Computer Science 2023-04-18 Ruchao Fan , Wei Chu , Peng Chang , Abeer Alwan

While Transformers have achieved promising results in end-to-end (E2E) automatic speech recognition (ASR), their autoregressive (AR) structure becomes a bottleneck for speeding up the decoding process. For real-world deployment, ASR systems…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-27 Keqi Deng , Zehui Yang , Shinji Watanabe , Yosuke Higuchi , Gaofeng Cheng , Pengyuan Zhang

We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a…

Computation and Language · Computer Science 2021-06-10 Cunxiao Du , Zhaopeng Tu , Jing Jiang

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Computation and Language · Computer Science 2023-02-09 Hongqiu Wu , Ruixue Ding , Hai Zhao , Pengjun Xie , Fei Huang , Min Zhang

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Machine Learning · Computer Science 2022-06-29 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude…

Computation and Language · Computer Science 2018-03-12 Jiatao Gu , James Bradbury , Caiming Xiong , Victor O. K. Li , Richard Socher

Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence. However, due to the lack of target dependency modelling in the decoder, the conditional generation process…

Computation and Language · Computer Science 2020-11-03 Liang Ding , Longyue Wang , Di Wu , Dacheng Tao , Zhaopeng Tu

End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-17 Yuya Fujita , Shinji Watanabe , Motoi Omachi , Xuankai Chan

We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face challenges with…

Machine Learning · Computer Science 2025-04-17 Andrew Kiruluta , Eric Lundy , Andreas Lemos

Autoregressive sequence Generation models have achieved state-of-the-art performance in areas like machine translation and image captioning. These models are autoregressive in that they generate each word by conditioning on previously…

Computation and Language · Computer Science 2021-01-26 Longteng Guo , Jing Liu , Xinxin Zhu , Hanqing Lu

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

Computation and Language · Computer Science 2022-11-23 Shunsuke Kitada , Hitoshi Iyatomi