English
Related papers

Related papers: An Exploration of Hierarchical Attention Transform…

200 papers

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Machine Learning · Computer Science 2025-04-22 Sushant Singh , Ausif Mahmood

The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation. In this work, we propose and compare several modifications of HAN in which the…

Computation and Language · Computer Science 2019-08-19 Jean-Baptiste Remy , Antoine Jean-Pierre Tixier , Michalis Vazirgiannis

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…

Computation and Language · Computer Science 2017-09-18 Nikolaos Pappas , Andrei Popescu-Belis

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in…

Computation and Language · Computer Science 2025-09-26 Ayan Sar , Sampurna Roy , Kanav Gupta , Anurag Kaushish , Tanupriya Choudhury , Abhijit Kumar

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…

Computation and Language · Computer Science 2020-01-06 Goran Glavaš , Swapna Somasundaran

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Computation and Language · Computer Science 2021-09-07 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

Utilizing pre-trained language models has achieved great success for neural document ranking. Limited by the computational and memory requirements, long document modeling becomes a critical issue. Recent works propose to modify the full…

Information Retrieval · Computer Science 2022-02-23 Yujia Zhou , Zhicheng Dou , Huaying Yuan , Zhengyi Ma

Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or…

Information Retrieval · Computer Science 2021-05-07 Liu Yang , Mingyang Zhang , Cheng Li , Michael Bendersky , Marc Najork

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we…

Computation and Language · Computer Science 2024-04-05 Hanrui Wang , Zhanghao Wu , Zhijian Liu , Han Cai , Ligeng Zhu , Chuang Gan , Song Han

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Yi Bin , Haoxuan Li , Yahui Xu , Xing Xu , Yang Yang , Heng Tao Shen

The Transformer has quickly become the dominant architecture for various pattern recognition tasks due to its capacity for long-range representation. However, transformers are data-hungry models and need large datasets for training. In…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Marwa Dhiaf , Ahmed Cheikh Rouhou , Yousri Kessentini , Sinda Ben Salem

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

Handwritten document recognition (HDR) is one of the most challenging tasks in the field of computer vision, due to the various writing styles and complex layouts inherent in handwritten texts. Traditionally, this problem has been…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Mohammed Hamdan , Abderrahmane Rahiche , Mohamed Cheriet

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Computation and Language · Computer Science 2021-06-01 Potsawee Manakul , Mark J. F. Gales

Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…

Computation and Language · Computer Science 2019-01-29 Ming-Wei Chang , Kristina Toutanova , Kenton Lee , Jacob Devlin

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

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Image and Video Processing · Electrical Eng. & Systems 2023-03-21 Xiangyu Chen , Xintao Wang , Jiantao Zhou , Yu Qiao , Chao Dong

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Xincheng Yang , Mingze Jin , Weiji He , Qian Chen

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…