Related papers: Augmenting Data with Mixup for Sentence Classifica…
Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pairs can boost…
Data augmentation in time series forecasting plays a crucial role in enhancing model performance by introducing variability while maintaining the underlying temporal patterns. However, time series data offers fewer augmentation strategies…
In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a…
Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thoughts and supervised…
Deep learning-based text classification models need abundant labeled data to obtain competitive performance. Unfortunately, annotating large-size corpus is time-consuming and laborious. To tackle this, multiple researches try to use data…
Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…
The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual…
This work develops \emph{mixup for graph data}. Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples. Traditionally, Mixup can work on…
Hierarchical vector field interpolation introduces a structured probabilistic framework for lexical representation, ensuring that word embeddings transition smoothly across a continuous manifold rather than being constrained to discrete…
Constructing dataset for fashion style recognition is challenging due to the inherent subjectivity and ambiguity of style concepts. Recent advances in text-to-image models have facilitated generative data augmentation by synthesizing images…
Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems. Recent approaches leverage mixup to calibrate the network's predictions…
Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. Recent work often tackles this problem using large language models (LLMs) like GPT3 that can…
Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data…
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 propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…
Deep Neural Networks (DNNs) are extensively used in collaborative filtering due to their impressive effectiveness. These systems depend on interaction data to learn user and item embeddings that are crucial for recommendations. However, the…
The Tsetlin Machine (TM) architecture has recently demonstrated effectiveness in Machine Learning (ML), particularly within Natural Language Processing (NLP). It has been utilized to construct word embedding using conjunctive propositional…
Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on…
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…