Related papers: Cropping outperforms dropout as an augmentation st…
Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of…
We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…
Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…
Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…
Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional…
Contrastive learning has recently established itself as a powerful self-supervised learning framework for extracting rich and versatile data representations. Broadly speaking, contrastive learning relies on a data augmentation scheme to…
Transformer-based language models have shown state-of-the-art performance on a variety of natural language understanding tasks. To achieve this performance, these models are first pre-trained on general corpus and then fine-tuned on…
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…
This study conducts a thorough evaluation of text augmentation techniques across a variety of datasets and natural language processing (NLP) tasks to address the lack of reliable, generalized evidence for these methods. It examines the…
Dropout is a well-known regularization method by sampling a sub-network from a larger deep neural network and training different sub-networks on different subsets of the data. Inspired by the dropout concept, we propose EDropout as an…
Embedding models are crucial to modern NLP. However, the creation of the most effective models relies on carefully constructed supervised finetuning data. For high resource languages, such as English, such datasets are readily available.…
Text embeddings are numerical representations of text data, where words, phrases, or entire documents are converted into vectors of real numbers. These embeddings capture semantic meanings and relationships between text elements in a…
Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on within-corpus scenarios during model pre-training, efficient dataset pruning…
We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…
Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…
Word Representations form the core component for almost all advanced Natural Language Processing (NLP) applications such as text mining, question-answering, and text summarization, etc. Over the last two decades, immense research is…
The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different…
Audio-text contrastive models have become a powerful approach in music representation learning. Despite their empirical success, however, little is known about the influence of key design choices on the quality of music-text representations…
Decoder-only LLM-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieval. In this work, we introduce NV-Embed, incorporating…
Reconstruction and joint embedding have emerged as two leading paradigms in Self Supervised Learning (SSL). Reconstruction methods focus on recovering the original sample from a different view in input space. On the other hand, joint…