English
Related papers

Related papers: ConvBERT: Improving BERT with Span-based Dynamic C…

200 papers

Large language Models (LLMs), though growing exceedingly powerful, comprises of orders of magnitude less neurons and synapses than the human brain. However, it requires significantly more power/energy to operate. In this work, we propose a…

Neural and Evolutionary Computing · Computer Science 2024-02-20 Malyaban Bal , Abhronil Sengupta

Sign language processing has traditionally relied on task-specific models, limiting the potential for transfer learning across tasks. Pre-training methods for sign language have typically focused on either supervised pre-training, which…

Computation and Language · Computer Science 2025-07-04 Shester Gueuwou , Xiaodan Du , Greg Shakhnarovich , Karen Livescu , Alexander H. Liu

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Sergey Zagoruyko , Nikos Komodakis

Unsupervised cross-lingual transfer involves transferring knowledge between languages without explicit supervision. Although numerous studies have been conducted to improve performance in such tasks by focusing on cross-lingual knowledge,…

Computation and Language · Computer Science 2024-04-26 Jianyu Zheng , Fengfei Fan , Jianquan Li

BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on…

Computation and Language · Computer Science 2024-12-11 Wen Liang , Youzhi Liang

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

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently…

Computation and Language · Computer Science 2020-10-19 Xiaoqi Jiao , Yichun Yin , Lifeng Shang , Xin Jiang , Xiao Chen , Linlin Li , Fang Wang , Qun Liu

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according…

Computation and Language · Computer Science 2020-04-07 Yile Wang , Leyang Cui , Yue Zhang

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

Computation and Language · Computer Science 2024-02-09 Yongyu Yan , Kui Xue , Xiaoming Shi , Qi Ye , Jingping Liu , Tong Ruan

Since the introduction of the original BERT (i.e., BASE BERT), researchers have developed various customized BERT models with improved performance for specific domains and tasks by exploiting the benefits of transfer learning. Due to the…

Computation and Language · Computer Science 2023-08-15 Jia Tracy Shen , Michiharu Yamashita , Ethan Prihar , Neil Heffernan , Xintao Wu , Ben Graff , Dongwon Lee

Current end-to-end machine reading and question answering (Q\&A) models are primarily based on recurrent neural networks (RNNs) with attention. Despite their success, these models are often slow for both training and inference due to the…

Computation and Language · Computer Science 2018-04-26 Adams Wei Yu , David Dohan , Minh-Thang Luong , Rui Zhao , Kai Chen , Mohammad Norouzi , Quoc V. Le

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Nam Hyeon-Woo , Kim Yu-Ji , Byeongho Heo , Dongyoon Han , Seong Joon Oh , Tae-Hyun Oh

Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…

Computation and Language · Computer Science 2021-01-27 Vinit Ravishankar , Artur Kulmizev , Mostafa Abdou , Anders Søgaard , Joakim Nivre

Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of…

Machine Learning · Computer Science 2021-05-18 Swetha Mandava , Szymon Migacz , Alex Fit Florea

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

Computation and Language · Computer Science 2022-05-05 Guy D. Rosin , Kira Radinsky

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…

Computation and Language · Computer Science 2020-07-28 Yang Fan , Shufang Xie , Yingce Xia , Lijun Wu , Tao Qin , Xiang-Yang Li , Tie-Yan Liu

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Xu Yang , Hanwang Zhang , Guojun Qi , Jianfei Cai

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

Currently, the most widespread neural network architecture for training language models is the so called BERT which led to improvements in various Natural Language Processing (NLP) tasks. In general, the larger the number of parameters in a…

Computation and Language · Computer Science 2021-11-02 Jochen Zöllner , Konrad Sperfeld , Christoph Wick , Roger Labahn