English
Related papers

Related papers: Long Short-Term Attention

200 papers

Chinese word segmentation (CWS) is the basic of Chinese natural language processing (NLP). The quality of word segmentation will directly affect the rest of NLP tasks. Recently, with the artificial intelligence tide rising again, Long…

Machine Learning · Computer Science 2021-05-21 Chen Jin , Zhuangwei Shi , Weihua Li , Yanbu Guo

Recently, the soft attention mechanism, which was originally proposed in language processing, has been applied in computer vision tasks like image captioning. This paper presents improvements to the soft attention model by combining a…

Computer Vision and Pattern Recognition · Computer Science 2017-05-22 Shiyang Yan , Jeremy S. Smith , Wenjin Lu , Bailing Zhang

Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits…

Machine Learning · Computer Science 2026-05-14 Hoang-Quan Nguyen , Sankalp Pandey , Khoa Luu

Scientist learn early on how to cite scientific sources to support their claims. Sometimes, however, scientists have challenges determining where a citation should be situated -- or, even worse, fail to cite a source altogether.…

Computation and Language · Computer Science 2024-05-21 Tong Zeng , Daniel E. Acuna

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…

Computation and Language · Computer Science 2026-05-08 Bowen Peng , Subho Ghosh , Jeffrey Quesnelle

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Machine Learning · Computer Science 2024-12-25 Tianyu Ruan , Shihua Zhang

Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time…

Machine Learning · Computer Science 2025-07-14 Vincenzo Dentamaro

Recurrent neural networks (RNNs) have many advantages over more traditional system identification techniques. They may be applied to linear and nonlinear systems, and they require fewer modeling assumptions. However, these neural network…

Systems and Control · Electrical Eng. & Systems 2022-04-08 Kaicheng Niu , Mi Zhou , Chaouki T. Abdallah , Mohammad Hayajneh

Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover,…

Applications · Statistics 2017-12-20 Niek Tax , Ilya Verenich , Marcello La Rosa , Marlon Dumas

In this paper, we propose and investigate a novel memory architecture for neural networks called Hierarchical Attentive Memory (HAM). It is based on a binary tree with leaves corresponding to memory cells. This allows HAM to perform memory…

Machine Learning · Computer Science 2016-02-24 Marcin Andrychowicz , Karol Kurach

With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Recurrent Neural Network (RNN) architectures with Long…

Machine Learning · Statistics 2018-07-17 Huan Song , Deepta Rajan , Jayaraman J. Thiagarajan , Andreas Spanias

The standard LSTM, although it succeeds in the modeling long-range dependences, suffers from a highly complex structure that can be simplified through modifications to its gate units. This paper was to perform an empirical comparison…

Neural and Evolutionary Computing · Computer Science 2016-12-13 Yuzhen Lu

Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and predict their next items. The accumulated user behavior records…

Information Retrieval · Computer Science 2021-02-19 Qiaoyu Tan , Jianwei Zhang , Ninghao Liu , Xiao Huang , Hongxia Yang , Jingren Zhou , Xia Hu

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Computation and Language · Computer Science 2026-03-30 Hongxiang Zhang , Yuan Tian , Tianyi Zhang

In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2016-12-28 AJ Piergiovanni , Chenyou Fan , Michael S. Ryoo

Recurrent Neural Networks with Long Short-Term Memory (LSTM) make use of gating mechanisms to mitigate exploding and vanishing gradients when learning long-term dependencies. For this reason, LSTMs and other gated RNNs are widely adopted,…

Machine Learning · Computer Science 2021-09-27 Federico Landi , Lorenzo Baraldi , Marcella Cornia , Rita Cucchiara

The success of Convolutional Neural Networks (CNNs) in computer vision is mainly driven by their strong inductive bias, which is strong enough to allow CNNs to solve vision-related tasks with random weights, meaning without learning.…

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

Computation and Language · Computer Science 2019-11-22 Guangxiang Zhao , Xu Sun , Jingjing Xu , Zhiyuan Zhang , Liangchen Luo

Question answering is an important and difficult task in the natural language processing domain, because many basic natural language processing tasks can be cast into a question answering task. Several deep neural network architectures have…

Computation and Language · Computer Science 2017-07-10 Fenglong Ma , Radha Chitta , Saurabh Kataria , Jing Zhou , Palghat Ramesh , Tong Sun , Jing Gao

Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows…

Machine Learning · Computer Science 2019-07-16 Matthew Spellings