English
Related papers

Related papers: Hard-Coded Gaussian Attention for Neural Machine T…

200 papers

In the past few years, attention mechanisms have become an indispensable component of end-to-end neural machine translation models. However, previous attention models always refer to some source words when predicting a target word, which…

Computation and Language · Computer Science 2017-06-01 Junhui Li , Muhua Zhu

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero

Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference. However, MQA can lead to quality degradation, and moreover it may not be desirable to train a separate model just for faster…

Computation and Language · Computer Science 2023-12-27 Joshua Ainslie , James Lee-Thorp , Michiel de Jong , Yury Zemlyanskiy , Federico Lebrón , Sumit Sanghai

Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. However, much of this work only relies on the shared vocabulary and…

Computation and Language · Computer Science 2021-06-03 Fuli Luo , Wei Wang , Jiahao Liu , Yijia Liu , Bin Bi , Songfang Huang , Fei Huang , Luo Si

Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple…

Computation and Language · Computer Science 2022-09-01 Zewei Sun , Shujian Huang , Xin-Yu Dai , Jiajun Chen

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective…

Computation and Language · Computer Science 2021-05-20 Kaiser Sun , Ana Marasović

Multi-head attention is a driving force behind state-of-the-art transformers, which achieve remarkable performance across a variety of natural language processing (NLP) and computer vision tasks. It has been observed that for many…

Machine Learning · Computer Science 2022-06-14 Tam Nguyen , Tan M. Nguyen , Dung D. Le , Duy Khuong Nguyen , Viet-Anh Tran , Richard G. Baraniuk , Nhat Ho , Stanley J. Osher

Current data-driven methodologies for point cloud matching demand extensive training time and computational resources, presenting significant challenges for model deployment and application. In the point cloud matching task, recent…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Alessandro Riva , Alessandro Raganato , Simone Melzi

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

Large multilingual models, such as mBERT, have shown promise in crosslingual transfer. In this work, we employ pruning to quantify the robustness and interpret layer-wise importance of mBERT. On four GLUE tasks, the relative drops in…

Computation and Language · Computer Science 2021-09-28 Aakriti Budhraja , Madhura Pande , Pratyush Kumar , Mitesh M. Khapra

Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to…

Computation and Language · Computer Science 2020-08-13 Shuai Zhang , Peng Zhang , Xindian Ma , Junqiu Wei , Ningning Wang , Qun Liu

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

Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods. However, dot-product attention only considers the pair-wise correlation between words,…

Computation and Language · Computer Science 2021-09-15 Shaolei Zhang , Yang Feng

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Motivated by the fact that most of the information relevant to the prediction of target tokens is drawn from the source sentence $S=s_1, \ldots, s_S$, we propose truncating the target-side window used for computing self-attention by making…

Machine Learning · Computer Science 2024-12-19 Ciprian Chelba , Mia Chen , Ankur Bapna , Noam Shazeer

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an additional…

Computation and Language · Computer Science 2018-09-12 Tamer Alkhouli , Gabriel Bretschner , Hermann Ney

The state-of-the-art speech enhancement has limited performance in speech estimation accuracy. Recently, in deep learning, the Transformer shows the potential to exploit the long-range dependency in speech by self-attention. Therefore, it…

Sound · Computer Science 2023-05-10 Yi Li , Yang Sun , Syed Mohsen Naqvi

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Xizhou Zhu , Dazhi Cheng , Zheng Zhang , Stephen Lin , Jifeng Dai

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…

Computation and Language · Computer Science 2021-09-15 Mozhdeh Gheini , Xiang Ren , Jonathan May