English
Related papers

Related papers: Query-Key Normalization for Transformers

200 papers

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…

Machine Learning · Computer Science 2026-04-02 Hariprasath Govindarajan , Per Sidén , Jacob Roll , Fredrik Lindsten

Rapid progress has been made towards question answering (QA) systems that can extract answers from text. Existing neural approaches make use of expensive bi-directional attention mechanisms or score all possible answer spans, limiting…

Computation and Language · Computer Science 2017-09-12 Jonathan Raiman , John Miller

The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-11 Axel Berg , Mark O'Connor , Miguel Tairum Cruz

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

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Computation and Language · Computer Science 2020-02-17 Genta Indra Winata , Samuel Cahyawijaya , Zhaojiang Lin , Zihan Liu , Pascale Fung

We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of…

Machine Learning · Computer Science 2024-04-30 Franz A. Heinsen

Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference time. In this paper, we build upon $k$NN-LM \citep{khandelwal20generalization}, which uses a…

Computation and Language · Computer Science 2021-09-20 Jean-Francois Ton , Walter Talbott , Shuangfei Zhai , Josh Susskind

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Computation and Language · Computer Science 2023-04-04 Viet H. Pham , Thang M. Pham , Giang Nguyen , Long Nguyen , Dien Dinh

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

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies…

Computation and Language · Computer Science 2025-10-13 Changjiang Gao , Zixian Huang , Jingyang Gong , Shujian Huang , Lei Li , Fei Yuan

Modern neural networks are over-parametrized. In particular, each rectified linear hidden unit can be modified by a multiplicative factor by adjusting input and output weights, without changing the rest of the network. Inspired by the…

Computer Vision and Pattern Recognition · Computer Science 2019-02-28 Pierre Stock , Benjamin Graham , Rémi Gribonval , Hervé Jégou

Transformers have achieved great success in machine learning applications. Normalization techniques, such as Layer Normalization (LayerNorm, LN) and Root Mean Square Normalization (RMSNorm), play a critical role in accelerating and…

Machine Learning · Computer Science 2023-10-27 Zixuan Jiang , Jiaqi Gu , Hanqing Zhu , David Z. Pan

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Computation and Language · Computer Science 2020-08-11 Sneha Mehta , Huzefa Rangwala , Naren Ramakrishnan

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…

Machine Learning · Computer Science 2020-10-14 Insoo Chung , Byeongwook Kim , Yoonjung Choi , Se Jung Kwon , Yongkweon Jeon , Baeseong Park , Sangha Kim , Dongsoo Lee

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a…

Computation and Language · Computer Science 2026-05-26 Haojie Ouyang , Jianwei Lv , Lei Ren , Chen Wei , Xiaojie Wang , Fangxiang Feng

Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute…

Computation and Language · Computer Science 2025-02-04 Gabriel Lindenmaier , Sean Papay , Sebastian Padó

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training…

Computation and Language · Computer Science 2016-09-27 Antonios Anastasopoulos , David Chiang , Long Duong

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…

Computation and Language · Computer Science 2021-06-02 Syrine Krichene , Thomas Müller , Julian Martin Eisenschlos