English
Related papers

Related papers: How Much Noise Can BERT Handle? Insights from Mult…

200 papers

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

We present a method for training a neural network to perform image denoising without access to clean training examples or access to paired noisy training examples. Our method requires only a single noisy realization of each training example…

Image and Video Processing · Electrical Eng. & Systems 2019-10-29 Nick Moran , Dan Schmidt , Yu Zhong , Patrick Coady

Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…

Machine Learning · Computer Science 2019-12-06 Yi Sun , Yan Tian , Yiping Xu , Jianxiang Li

In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy. Previous works have shown that significant…

Computation and Language · Computer Science 2019-11-06 Lukas Lange , Michael A. Hedderich , Dietrich Klakow

Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…

Computation and Language · Computer Science 2021-03-19 Daniel Loureiro , Kiamehr Rezaee , Mohammad Taher Pilehvar , Jose Camacho-Collados

Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models. In…

Computation and Language · Computer Science 2023-03-14 Mohamed Nabih Ali , Alessio Brutti , Daniele Falavigna

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

Machine Learning · Computer Science 2025-10-30 Kuan Zhang , Chengliang Chai , Jingzhe Xu , Chi Zhang , Han Han , Ye Yuan , Guoren Wang , Lei Cao

In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance…

Computation and Language · Computer Science 2021-08-30 Ryo Nagata , Manabu Kimura , Kazuaki Hanawa

Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise…

Machine Learning · Computer Science 2025-05-06 Hao Chen , Zihan Wang , Ran Tao , Hongxin Wei , Xing Xie , Masashi Sugiyama , Bhiksha Raj , Jindong Wang

The supervised training of high-capacity models on large datasets containing hundreds of thousands of document-summary pairs is critical to the recent success of deep learning techniques for abstractive summarization. Unfortunately, in most…

Computation and Language · Computer Science 2020-04-22 Reinald Kim Amplayo , Mirella Lapata

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…

Computation and Language · Computer Science 2023-02-14 Asa Cooper Stickland , Sailik Sengupta , Jason Krone , Saab Mansour , He He

During both pretraining and fine-tuning, Large Language Models (\textbf{LLMs}) are trained on trillions of tokens of text of widely varying quality. Both phases of training typically involve heuristically filtering out ``low-quality'' or…

Machine Learning · Computer Science 2024-02-12 Alex Havrilla , Maia Iyer

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.…

Sound · Computer Science 2021-09-21 Madhav Mahesh Kashyap , Anuj Tambwekar , Krishnamoorthy Manohara , S Natarajan

We study the problem of few-shot learning-based denoising where the training set contains just a handful of clean and noisy samples. A solution to mitigate the small training set issue is to pre-train a denoising model with small training…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Leslie Casas , Attila Klimmek , Gustavo Carneiro , Nassir Navab , Vasileios Belagiannis

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method…

Computer Vision and Pattern Recognition · Computer Science 2020-08-07 Chuanyi Zhang , Yazhou Yao , Xiangbo Shu , Zechao Li , Zhenmin Tang , Qi Wu

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

In this work, we induce character-level noise in various forms when fine-tuning BERT to enable zero-shot cross-lingual transfer to unseen dialects and languages. We fine-tune BERT on three sentence-level classification tasks and evaluate…

Computation and Language · Computer Science 2023-04-03 Aarohi Srivastava , David Chiang

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and…

Computation and Language · Computer Science 2024-09-19 Xingyun Hong , Yan Shao , Zhilin Wang , Manni Duan , Jin Xiongnan

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…

Machine Learning · Computer Science 2022-12-05 Sumyeong Ahn , Se-Young Yun

Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels…

Machine Learning · Computer Science 2018-07-24 Michael A. Hedderich , Dietrich Klakow