English
Related papers

Related papers: Transformers without Tears: Improving the Normaliz…

200 papers

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of…

Computation and Language · Computer Science 2023-10-18 Woohyeon Moon , Taeyoung Kim , Bumgeun Park , Dongsoo Har

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

Computation and Language · Computer Science 2023-10-31 Yangjun Wu , Kebin Fang , Dongxiang Zhang , Han Wang , Hao Zhang , Gang Chen

Large Transformer models have been central to recent advances in natural language processing. The training and inference costs of these models, however, have grown rapidly and become prohibitively expensive. Here we aim to reduce the costs…

Machine Learning · Computer Science 2022-01-26 David R. So , Wojciech Mańke , Hanxiao Liu , Zihang Dai , Noam Shazeer , Quoc V. Le

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

We find that current text embedding models produce outputs with a consistent bias, i.e., each embedding vector $e$ can be decomposed as $\tilde{e} + \mu$, where $\mu$ is almost identical across all sentences. We propose a plug-and-play,…

Computation and Language · Computer Science 2025-11-17 Xingyu Ren , Youran Sun , Haoyu Liang

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Chen Zhu , Wei Ping , Chaowei Xiao , Mohammad Shoeybi , Tom Goldstein , Anima Anandkumar , Bryan Catanzaro

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Computation and Language · Computer Science 2026-02-02 Chao Wang , Bei Li , Jiaqi Zhang , Xinyu Liu , Yuchun Fan , Linkun Lyu , Xin Chen , Jingang Wang , Tong Xiao , Peng Pei , Xunliang Cai

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

Machine Learning · Computer Science 2021-09-28 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…

Machine Learning · Computer Science 2021-07-28 Danielle Rothermel , Margaret Li , Tim Rocktäschel , Jakob Foerster

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which…

Computation and Language · Computer Science 2022-12-21 Roshan Sharma , Bhiksha Raj

Language model (LM) pre-training has resulted in impressive performance and sample efficiency on a variety of language understanding tasks. However, it remains unclear how to best use pre-trained LMs for generation tasks such as abstractive…

Computation and Language · Computer Science 2019-05-23 Urvashi Khandelwal , Kevin Clark , Dan Jurafsky , Lukasz Kaiser

This work analyzes the training dynamics of Image Restoration (IR) Transformers and uncovers a critical yet overlooked issue: conventional LayerNorm (LN) drives feature magnitudes to diverge to a million scale and collapses channel-wise…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 MinKyu Lee , Sangeek Hyun , Woojin Jun , Hyunjun Kim , Jiwoo Chung , Jae-Pil Heo

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…

Computation and Language · Computer Science 2023-09-18 Luca Di Liello

The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and representational capacity. Prior attempts to combine their strengths…

Machine Learning · Computer Science 2026-05-22 Tianyu Li , Dongchen Han , Zixuan Cao , Haofeng Huang , Mengyu Zhou , Ming Chen , Erchao Zhao , Xiaoxi Jiang , Guanjun Jiang , Gao Huang

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quantization in…

Machine Learning · Computer Science 2024-10-14 Kamran Chitsaz , Quentin Fournier , Gonçalo Mordido , Sarath Chandar

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

Computation and Language · Computer Science 2021-01-29 Manoj Kumar , Varun Kumar , Hadrien Glaude , Cyprien delichy , Aman Alok , Rahul Gupta

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow…

Machine Learning · Computer Science 2020-06-30 Ruibin Xiong , Yunchang Yang , Di He , Kai Zheng , Shuxin Zheng , Chen Xing , Huishuai Zhang , Yanyan Lan , Liwei Wang , Tie-Yan Liu