English
Related papers

Related papers: Local Self-Attention over Long Text for Efficient …

200 papers

The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time series prediction. However, its core component,…

Machine Learning · Computer Science 2025-07-24 Haolin Jin , Mengbai Xiao , Yuan Yuan , Xiao Zhang , Dongxiao Yu , Guanghui Zhang , Haoliang Wang

We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-attention. Self-attention requires the key-value (KV) cache of…

Computation and Language · Computer Science 2024-11-04 Namgyu Ho , Sangmin Bae , Taehyeon Kim , Hyunjik Jo , Yireun Kim , Tal Schuster , Adam Fisch , James Thorne , Se-Young Yun

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Computation and Language · Computer Science 2019-11-12 Zihao Ye , Qipeng Guo , Quan Gan , Xipeng Qiu , Zheng Zhang

Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling…

Machine Learning · Computer Science 2022-06-17 Haixu Wu , Jialong Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuxuan Liang , Pan Zhou , Roger Zimmermann , Shuicheng Yan

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…

Computation and Language · Computer Science 2022-12-09 Aydar Bulatov , Yuri Kuratov , Mikhail S. Burtsev

Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Ting Yao , Yehao Li , Yingwei Pan , Yu Wang , Xiao-Ping Zhang , Tao Mei

The primary goal of ad-hoc retrieval (document retrieval in the context of question answering) is to find relevant documents satisfied the information need posted in a natural language query. It requires a good understanding of the query…

Information Retrieval · Computer Science 2019-11-05 Tolgahan Cakaloglu , Xiaowei Xu

Document-level MT models are still far from satisfactory. Existing work extend translation unit from single sentence to multiple sentences. However, study shows that when we further enlarge the translation unit to a whole document,…

Computation and Language · Computer Science 2021-06-01 Guangsheng Bao , Yue Zhang , Zhiyang Teng , Boxing Chen , Weihua Luo

Attention mechanism, including global attention and local attention, plays a key role in neural machine translation (NMT). Global attention attends to all source words for word prediction. In comparison, local attention selectively looks at…

Computation and Language · Computer Science 2019-09-20 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita , Tiejun Zhao

Autoregressive Transformers are strong language models but incur O(T) complexity during per-token generation due to the self-attention mechanism. Recent work proposes kernel-based methods to approximate causal self-attention by replacing it…

Machine Learning · Computer Science 2022-10-11 Huanru Henry Mao

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Chunyang Wu , Yongqiang Wang , Yangyang Shi , Ching-Feng Yeh , Frank Zhang

Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks. Recent works have shown that attention-based models can benefit from more focused attention over local regions.…

Computation and Language · Computer Science 2021-05-25 Zhongli Li , Qingyu Zhou , Chao Li , Ke Xu , Yunbo Cao

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of token pairs in the input sequences and depends quadratically…

Machine Learning · Computer Science 2021-11-19 Zhanpeng Zeng , Yunyang Xiong , Sathya N. Ravi , Shailesh Acharya , Glenn Fung , Vikas Singh

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural…

Information Retrieval · Computer Science 2021-08-20 Jimmy Lin , Rodrigo Nogueira , Andrew Yates

The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs:…

Computation and Language · Computer Science 2026-02-06 Siran Liu , Guoxia Wang , Sa Wang , Jinle Zeng , HaoYang Xie , Siyu Lou , JiaBin Yang , DianHai Yu , Haifeng Wang , Chao Yang
‹ Prev 1 4 5 6 7 8 10 Next ›