English
Related papers

Related papers: Transformers without Tears: Improving the Normaliz…

200 papers

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's…

Computation and Language · Computer Science 2024-02-16 Yaoyiran Li , Edoardo M. Ponti , Ivan Vulić , Anna Korhonen

Transformer neural networks (TNN) demonstrated state-of-art performance on many natural language processing (NLP) tasks, replacing recurrent neural networks (RNNs), such as LSTMs or GRUs. However, TNNs did not perform well in speech…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-12 Jaeyoung Kim , Mostafa El-Khamy , Jungwon Lee

Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attention mechanism's linear…

Machine Learning · Computer Science 2026-04-22 Weijie Zhao , Mingquan Liu , Bolun Wang , Simo Wu , Nuobei Xie , Rui-Jie Zhu , Peng Zhou

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

Computation and Language · Computer Science 2020-12-24 Shaolei Zhang , Yang Feng , Liangyou Li

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…

Machine Learning · Computer Science 2023-05-19 Fuzhao Xue , Jianghai Chen , Aixin Sun , Xiaozhe Ren , Zangwei Zheng , Xiaoxin He , Yongming Chen , Xin Jiang , Yang You

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Machine Learning · Computer Science 2019-09-10 Dilin Wang , Chengyue Gong , Qiang Liu

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the Hessian matrix, and the maximum tolerable learning rate. We…

Machine Learning · Computer Science 2026-02-03 Marco Chen , Xianbiao Qi , Yelin He , Jiaquan Ye , Rong Xiao

Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the…

Computation and Language · Computer Science 2020-09-22 Pei Zhang , Boxing Chen , Niyu Ge , Kai Fan

Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…

Computation and Language · Computer Science 2022-10-27 Yile Wang , Linyi Yang , Zhiyang Teng , Ming Zhou , Yue Zhang

Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without…

Machine Learning · Computer Science 2026-05-26 Rao Fu , Zixuan Yang , Jiankun Zhang , Jing Ma , Hechang Chen , Yu Li , Yi Chang

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we…

Computation and Language · Computer Science 2021-06-16 Bo Zheng , Li Dong , Shaohan Huang , Wenhui Wang , Zewen Chi , Saksham Singhal , Wanxiang Che , Ting Liu , Xia Song , Furu Wei

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Machine Learning · Computer Science 2024-06-05 Phoebe Klett , Thomas Ahle

Transformer-based large language models have displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning by simply augmenting the query with some input-output examples from that…

Machine Learning · Computer Science 2024-06-18 Hongkang Li , Meng Wang , Songtao Lu , Xiaodong Cui , Pin-Yu Chen

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

While there have been several contributions exploring state of the art techniques for text normalization, the problem of inverse text normalization (ITN) remains relatively unexplored. The best known approaches leverage finite state…

Computation and Language · Computer Science 2021-02-15 Monica Sunkara , Chaitanya Shivade , Sravan Bodapati , Katrin Kirchhoff

Transformer architecture achieves great success in abundant natural language processing tasks. The over-parameterization of the Transformer model has motivated plenty of works to alleviate its overfitting for superior performances. With…

Computation and Language · Computer Science 2021-04-13 Zhen Wu , Lijun Wu , Qi Meng , Yingce Xia , Shufang Xie , Tao Qin , Xinyu Dai , Tie-Yan Liu

Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (LN) normalizes activations within each token to boost the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-03 Qiming Yang , Kai Zhang , Chaoxiang Lan , Zhi Yang , Zheyang Li , Wenming Tan , Jun Xiao , Shiliang Pu