English
Related papers

Related papers: A Length-Extrapolatable Transformer

200 papers

A promising approach to preserving model performance in linearized transformers is to employ position-based re-weighting functions. However, state-of-the-art re-weighting functions rely heavily on target sequence lengths, making it…

Computation and Language · Computer Science 2024-05-24 Victor Agostinelli , Sanghyun Hong , Lizhong Chen

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Computation and Language · Computer Science 2020-07-09 Prajjwal Bhargava

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Transformer models achieve state-of-the-art performance on a wide range of NLP tasks. They however suffer from a prohibitive limitation due to the self-attention mechanism, inducing $O(n^2)$ complexity with regard to sequence length. To…

Computation and Language · Computer Science 2022-10-28 Charles Condevaux , Sébastien Harispe

A recent variation of Transformer, Performer, scales Transformer to longer sequences with a linear attention mechanism. However, it is not compatible with relative position encoding, which has advantages over absolute position encoding. In…

Computation and Language · Computer Science 2021-09-09 Peng Chen

Transformer language models have demonstrated impressive generalization capabilities in natural language domains, yet we lack a fine-grained understanding of how such generalization arises. In this paper, we investigate length…

Computation and Language · Computer Science 2025-08-05 Ziyang Cai , Nayoung Lee , Avi Schwarzschild , Samet Oymak , Dimitris Papailiopoulos

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

Linear position interpolation helps pre-trained models using rotary position embeddings (RoPE) to extrapolate to longer sequence lengths. We propose using linear position interpolation to extend the extrapolation range of models using…

Computation and Language · Computer Science 2023-10-23 Faisal Al-Khateeb , Nolan Dey , Daria Soboleva , Joel Hestness

The use of Transformer architectures has facilitated remarkable progress in speech enhancement. Training Transformers using substantially long speech utterances is often infeasible as self-attention suffers from quadratic complexity. It is…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-18 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input. Most current…

Computation and Language · Computer Science 2022-08-18 Hai Pham , Guoxin Wang , Yijuan Lu , Dinei Florencio , Cha Zhang

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

Computation and Language · Computer Science 2019-11-07 Xindian Ma , Peng Zhang , Shuai Zhang , Nan Duan , Yuexian Hou , Dawei Song , Ming Zhou

Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing…

Computation and Language · Computer Science 2025-09-23 Ali Veisi , Hamidreza Amirzadeh , Amir Mansourian

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Length extrapolation permits training a transformer language model on short sequences that preserves perplexities when tested on substantially longer sequences. A relative positional embedding design, ALiBi, has had the widest usage to…

Computation and Language · Computer Science 2023-05-25 Ta-Chung Chi , Ting-Han Fan , Alexander I. Rudnicky , Peter J. Ramadge

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Computation and Language · Computer Science 2021-09-28 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

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

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a…

Machine Learning · Computer Science 2019-06-04 Zihang Dai , Zhilin Yang , Yiming Yang , Jaime Carbonell , Quoc V. Le , Ruslan Salakhutdinov