English
Related papers

Related papers: Transformers without Tears: Improving the Normaliz…

200 papers

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following…

Computation and Language · Computer Science 2022-05-25 Tao Lei , Ran Tian , Jasmijn Bastings , Ankur P. Parikh

Transformers have demonstrated exceptional performance across various domains due to their self-attention mechanism, which captures complex relationships in data. However, training on smaller datasets poses challenges, as standard attention…

Computation and Language · Computer Science 2024-12-10 Minhajur Rahman , Yasir Arafat

While recurrent neural networks still largely define state-of-the-art speech recognition systems, the Transformer network has been proven to be a competitive alternative, especially in the offline condition. Most studies with Transformers…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-13 Liang Lu , Changliang Liu , Jinyu Li , Yifan Gong

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Junyi Peng , Themos Stafylakis , Rongzhi Gu , Oldřich Plchot , Ladislav Mošner , Lukáš Burget , Jan Černocký

Nowadays, attention models are one of the popular candidates for speech recognition. So far, many studies mainly focus on the encoder structure or the attention module to enhance the performance of these models. However, mostly ignore the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Tobias Watzel , Ludwig Kürzinger , Lujun Li , Gerhard Rigoll

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Computation and Language · Computer Science 2018-05-08 Biao Zhang , Deyi Xiong , Jinsong Su

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jialong Guo , Xinghao Chen , Yehui Tang , Yunhe Wang

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

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Computation and Language · Computer Science 2020-04-02 Prakhar Thapak , Prodip Hore

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…

Computation and Language · Computer Science 2020-12-07 Daniel Grießhaber , Johannes Maucher , Ngoc Thang Vu

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Computation and Language · Computer Science 2023-07-27 Tong Guo

Layer Normalization (LayerNorm) is one of the fundamental components in transformers that stabilizes training and improves optimization. In recent times, Pre-LayerNorm transformers have become the preferred choice over Post-LayerNorm…

Machine Learning · Computer Science 2025-11-14 Rishi Singhal , Jung-Eun Kim

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

Computation and Language · Computer Science 2022-10-25 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-06 Matthew Wiesner , Adithya Renduchintala , Shinji Watanabe , Chunxi Liu , Najim Dehak , Sanjeev Khudanpur

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Machine Learning · Computer Science 2026-02-02 Shyam Venkatasubramanian , Sean Moushegian , Michael Lin , Mir Park , Ankit Singhal , Connor Lee