Related papers: To Augment or Not to Augment? A Comparative Study …

Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we…

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in…

Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements…

The generative large language models (LLMs) are increasingly used for data augmentation tasks, where text samples are paraphrased (or generated anew) and then used for classifier fine-tuning. Existing works on augmentation leverage the…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

Machine learning models can reach high performance on benchmark natural language processing (NLP) datasets but fail in more challenging settings. We study this issue when a pre-trained model learns dataset artifacts in natural language…

The current era of natural language processing (NLP) has been defined by the prominence of pre-trained language models since the advent of BERT. A feature of BERT and models with similar architecture is the objective of masked language…

The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks. In this era of open-ended…

Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure,…

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmentation enhancement strategy for neural machine translation.…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…

Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or…

Data augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions that map the original samples into the…

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…

Type- and token-based embedding architectures are still competing in lexical semantic change detection. The recent success of type-based models in SemEval-2020 Task 1 has raised the question why the success of token-based models on a…

Lately, instruction-based techniques have made significant strides in improving performance in few-shot learning scenarios. They achieve this by bridging the gap between pre-trained language models and fine-tuning for specific downstream…