English
Related papers

Related papers: Of Non-Linearity and Commutativity in BERT

200 papers

Transformer based architectures have become de-facto models used for a range of Natural Language Processing tasks. In particular, the BERT based models achieved significant accuracy gain for GLUE tasks, CoNLL-03 and SQuAD. However, BERT…

Computation and Language · Computer Science 2021-04-21 Sheng Shen , Zhen Dong , Jiayu Ye , Linjian Ma , Zhewei Yao , Amir Gholami , Michael W. Mahoney , Kurt Keutzer

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

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Computation and Language · Computer Science 2024-06-21 Martin Courtois , Malte Ostendorff , Leonhard Hennig , Georg Rehm

We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency, with their impact signifying as model size increases. This finding highlights a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Xuwei Xu , Yang Li , Yudong Chen , Jiajun Liu , Sen Wang

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Computation and Language · Computer Science 2019-09-12 Betty van Aken , Benjamin Winter , Alexander Löser , Felix A. Gers

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the…

Machine Learning · Computer Science 2021-09-23 Shuangfei Zhai , Walter Talbott , Nitish Srivastava , Chen Huang , Hanlin Goh , Ruixiang Zhang , Josh Susskind

The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper,…

Machine Learning · Computer Science 2026-02-10 Ambroise Odonnat , Laetitia Chapel , Romain Tavenard , Ievgen Redko

Structural probes learn a linear transformation to find how dependency trees are embedded in the hidden states of language models. This simple design may not allow for full exploitation of the structure of the encoded information. Hence, to…

Computation and Language · Computer Science 2024-02-27 Avik Pal , Madhura Pawar

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

Computation and Language · Computer Science 2020-02-18 Jinhua Zhu , Yingce Xia , Lijun Wu , Di He , Tao Qin , Wengang Zhou , Houqiang Li , Tie-Yan Liu

Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Srinadh Bhojanapalli , Ayan Chakrabarti , Daniel Glasner , Daliang Li , Thomas Unterthiner , Andreas Veit

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental…

Machine Learning · Computer Science 2022-04-15 Liangqiong Qu , Yuyin Zhou , Paul Pu Liang , Yingda Xia , Feifei Wang , Ehsan Adeli , Li Fei-Fei , Daniel Rubin

Fine-tuning pre-trained transformer-based language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks. Despite the strong empirical performance of fine-tuned models, fine-tuning is an…

Machine Learning · Computer Science 2021-03-26 Marius Mosbach , Maksym Andriushchenko , Dietrich Klakow

Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-18 Jinle Zeng , Min Li , Zhihua Wu , Jiaqi Liu , Yuang Liu , Dianhai Yu , Yanjun Ma

Transformer-based pretrained models like BERT, GPT-2 and T5 have been finetuned for a large number of natural language processing (NLP) tasks, and have been shown to be very effective. However, while finetuning, what changes across layers…

Computation and Language · Computer Science 2023-11-09 Pavan Kalyan Reddy Neerudu , Subba Reddy Oota , Mounika Marreddy , Venkateswara Rao Kagita , Manish Gupta

Transformer models have revolutionized AI tasks, but their large size hinders real-world deployment on resource-constrained and latency-critical edge devices. While binarized Transformers offer a promising solution by significantly reducing…

Machine Learning · Computer Science 2025-05-13 Yuhao Ji , Chao Fang , Shaobo Ma , Haikuo Shao , Zhongfeng Wang

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

Despite their nearly universal adoption for large language models, the internal workings of transformers are not well understood. We aim to better understand the impact of removing or reorganizing information throughout the layers of a…

Computation and Language · Computer Science 2025-02-14 Qi Sun , Marc Pickett , Aakash Kumar Nain , Llion Jones

Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by…

Computation and Language · Computer Science 2021-06-28 Weihao Yu , Zihang Jiang , Fei Chen , Qibin Hou , Jiashi Feng