English
Related papers

Related papers: Monotonic Multihead Attention

200 papers

Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the…

Computation and Language · Computer Science 2019-11-22 Zewei Sun , Shujian Huang , Hao-Ran Wei , Xin-yu Dai , Jiajun Chen

Scaling pre-trained language models has resulted in large performance gains in various natural language processing tasks but comes with a large cost in memory requirements. Inspired by the position embeddings in transformers, we aim to…

Computation and Language · Computer Science 2023-10-13 Huiyin Xue , Nikolaos Aletras

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

Computation and Language · Computer Science 2017-11-06 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of…

Computation and Language · Computer Science 2016-01-07 Orhan Firat , Kyunghyun Cho , Yoshua Bengio

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-28 Rui Wang , Junyi Ao , Long Zhou , Shujie Liu , Zhihua Wei , Tom Ko , Qing Li , Yu 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

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

Attention is a powerful and ubiquitous mechanism for allowing neural models to focus on particular salient pieces of information by taking their weighted average when making predictions. In particular, multi-headed attention is a driving…

Computation and Language · Computer Science 2019-11-05 Paul Michel , Omer Levy , Graham Neubig

Soft attention is a critical mechanism powering LLMs to locate relevant parts within a given context. However, individual attention weights are determined by the similarity of only a single query and key token vector. This "single token…

Computation and Language · Computer Science 2025-07-14 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word. However, we find that the…

Computation and Language · Computer Science 2017-08-31 Long Zhou , Jiajun Zhang , Chengqing Zong

Sequence expansion between encoder and decoder is a critical challenge in sequence-to-sequence TTS. Attention-based methods achieve great naturalness but suffer from unstable issues like missing and repeating phonemes, not to mention…

Sound · Computer Science 2022-03-21 Yunchao He , Jian Luan , Yujun Wang

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Computation and Language · Computer Science 2020-04-02 Prakhar Thapak , Prodip Hore

Transformers have advanced the field of natural language processing (NLP) on a variety of important tasks. At the cornerstone of the Transformer architecture is the multi-head attention (MHA) mechanism which models pairwise interactions…

Computation and Language · Computer Science 2021-06-01 Lin Zheng , Zhiyong Wu , Lingpeng Kong

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Dimitrios Konstantinidis , Ilias Papastratis , Kosmas Dimitropoulos , Petros Daras

We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM)…

Machine Learning · Computer Science 2022-11-24 Kieran Wood , Sven Giegerich , Stephen Roberts , Stefan Zohren

Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Pooyan Rahmanzadehgervi , Hung Huy Nguyen , Rosanne Liu , Long Mai , Anh Totti Nguyen

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

Computation and Language · Computer Science 2022-10-12 Xiaofeng Zhang , Yikang Shen , Zeyu Huang , Jie Zhou , Wenge Rong , Zhang Xiong

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Computation and Language · Computer Science 2025-09-19 Yanming Kang , Giang Tran , Hans De Sterck

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable…

Computation and Language · Computer Science 2022-10-27 Albert Zeyer , Robin Schmitt , Wei Zhou , Ralf Schlüter , Hermann Ney