English
Related papers

Related papers: Monotonic Multihead Attention

200 papers

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Thanh-Dat Truong , Christophe Bobda , Nitin Agarwal , Khoa Luu

In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we propose Multi-head Explicit Attention (MEA), a simple yet…

Machine Learning · Computer Science 2026-01-28 Runyu Peng , Yunhua Zhou , Demin Song , Kai Lv , Bo Wang , Qipeng Guo , Xipeng Qiu

Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized…

Computation and Language · Computer Science 2021-04-09 Annette Rios , Chantal Amrhein , Noëmi Aepli , Rico Sennrich

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

The self-attention mechanism, at the heart of the Transformer model, is able to effectively model pairwise interactions between tokens. However, numerous recent works have shown that it is unable to perform basic tasks involving detecting…

Machine Learning · Computer Science 2026-02-03 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attention by allowing a model to jointly attend information from…

Machine Learning · Computer Science 2020-11-03 Bang An , Jie Lyu , Zhenyi Wang , Chunyuan Li , Changwei Hu , Fei Tan , Ruiyi Zhang , Yifan Hu , Changyou Chen

Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to…

Computation and Language · Computer Science 2017-04-24 Jindřich Libovický , Jindřich Helcl

Recently, there has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the…

Computation and Language · Computer Science 2022-07-07 Veneta Haralampieva , Ozan Caglayan , Lucia Specia

Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate sequences in parallel via tree attention with a fixed…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Zhendong Zhang

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using…

Computation and Language · Computer Science 2019-03-27 Tao Shen , Tianyi Zhou , Guodong Long , Jing Jiang , Chengqi Zhang

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

Computation and Language · Computer Science 2018-07-31 Tomoki Hayashi , Shinji Watanabe , Tomoki Toda , Kazuya Takeda

Attention-based autoregressive models have achieved state-of-the-art performance in various sequence-to-sequence tasks, including Text-To-Speech (TTS) and Neural Machine Translation (NMT), but can be difficult to train. The standard…

Computation and Language · Computer Science 2022-11-08 Qingyun Dou , Mark Gales

Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are common scenarios…

Computation and Language · Computer Science 2021-06-22 Hongyu Gong , Yun Tang , Juan Pino , Xian Li

The attention mechanism is an important part of the neural machine translation (NMT) where it was reported to produce richer source representation compared to fixed-length encoding sequence-to-sequence models. Recently, the effectiveness of…

Computation and Language · Computer Science 2016-09-14 Ozan Caglayan , Loïc Barrault , Fethi Bougares

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

Multi-head attention powers Transformer networks, the primary deep learning architecture behind the success of large language models (LLMs). Yet, the theoretical advantages of multi-head versus single-head attention, beyond mere parallel…

Machine Learning · Computer Science 2025-11-11 Haitz Sáez de Ocáriz Borde

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

This document provides a brief introduction to the attention mechanism used in modern language models based on the Transformer architecture. We first illustrate how text is encoded as vectors and how the attention mechanism processes these…

Numerical Analysis · Mathematics 2026-04-02 Michel Fabrice Serret

Simultaneous or streaming machine translation generates translation while reading the input stream. These systems face a quality/latency trade-off, aiming to achieve high translation quality similar to non-streaming models with minimal…

Computation and Language · Computer Science 2025-03-31 Zeeshan Ahmed , Frank Seide , Zhe Liu , Rastislav Rabatin , Jachym Kolar , Niko Moritz , Ruiming Xie , Simone Merello , Christian Fuegen

The vanilla self-attention mechanism in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically induced by inputs and whose hidden dimension is equal to the sequence length $N$. As the context extends, the…

Machine Learning · Computer Science 2026-05-12 Qishuai Wen , Zhiyuan Huang , Xianghan Meng , Wei He , Chun-Guang Li