English
Related papers

Related papers: Regularization techniques for fine-tuning in neura…

200 papers

End-to-end speech-to-text translation typically suffers from the scarcity of paired speech-text data. One way to overcome this shortcoming is to utilize the bitext data from the Machine Translation (MT) task and perform Multi-Task Learning…

Computation and Language · Computer Science 2025-09-15 JungHo Jung , Junhyun Lee

The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Sherwin Bahmani , Oliver Hahn , Eduard Zamfir , Nikita Araslanov , Daniel Cremers , Stefan Roth

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

We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the…

Computer Vision and Pattern Recognition · Computer Science 2016-07-28 Muhammad Ghifary , W. Bastiaan Kleijn , Mengjie Zhang

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

Neural and Evolutionary Computing · Computer Science 2015-07-08 Aram Ter-Sarkisov , Holger Schwenk , Loic Barrault , Fethi Bougares

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Computation and Language · Computer Science 2022-11-07 Shuhao Gu , Bojie Hu , Yang Feng

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…

This paper presents Domain-Specific Sub-network (DoSS). It uses a set of masks obtained through pruning to define a sub-network for each domain and finetunes the sub-network parameters on domain data. This performs very closely and…

Computation and Language · Computer Science 2022-10-19 Amr Hendy , Mohamed Abdelghaffar , Mohamed Afify , Ahmed Y. Tawfik

Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a…

Computation and Language · Computer Science 2018-11-06 Jiacheng Zhang , Yang Liu , Huanbo Luan , Jingfang Xu , Maosong Sun

Dropout has proven to be an effective technique for regularization and preventing the co-adaptation of neurons in deep neural networks (DNN). It randomly drops units with a probability $p$ during the training stage of DNN. Dropout also…

Machine Learning · Computer Science 2018-08-30 Zongjie Ma , Abdul Sattar , Jun Zhou , Qingliang Chen , Kaile Su

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Computation and Language · Computer Science 2021-02-15 Haoming Jiang , Chen Liang , Chong Wang , Tuo Zhao

A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior…

Neural and Evolutionary Computing · Computer Science 2018-04-24 Najeeb Khan , Jawad Shah , Ian Stavness

Noise injection (NI) is an efficient technique to mitigate over-fitting in neural networks (NNs). The Bernoulli NI procedure as implemented in dropout and shakeout has connections with $l_1$ and $l_2$ regularization for the NN model…

Machine Learning · Statistics 2021-06-28 Yinan Li , Fang Liu

Training a deep neural network with a small amount of data is a challenging problem as it is vulnerable to overfitting. However, one of the practical difficulties that we often face is to collect many samples. Transfer learning is a…

Machine Learning · Computer Science 2020-07-13 Yunho Jeon , Yongseok Choi , Jaesun Park , Subin Yi , Dongyeon Cho , Jiwon Kim

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-08 Zhedong Zheng , Yi Yang

Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation…

Computation and Language · Computer Science 2022-05-26 Xin Zheng , Zhirui Zhang , Shujian Huang , Boxing Chen , Jun Xie , Weihua Luo , Jiajun Chen

Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect…

Machine Learning · Computer Science 2020-10-16 Colin Wei , Sham Kakade , Tengyu Ma

Neural Machine Translation (NMT) models are sensitive to small perturbations in the input. Robustness to such perturbations is typically measured using translation quality metrics such as BLEU on the noisy input. This paper proposes…

Computation and Language · Computer Science 2020-05-05 Xing Niu , Prashant Mathur , Georgiana Dinu , Yaser Al-Onaizan

One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation…

Computation and Language · Computer Science 2023-03-06 Amit Kumar , Rupjyoti Baruah , Ajay Pratap , Mayank Swarnkar , Anil Kumar Singh