Robin Gras
YOU?
Author Swipe
Genetic-Based Lottery Ticket Pruning for Transformers in Sentiment Classification: Realized Through Lottery Sample Selection Open
In the growing field of Natural Language Processing (NLP), transformers have become excessively large, pushing the boundaries of both training and inference compute. Given the size and widespread use of these models, there is now a strong …
A novel unsupervised fine-tuning method for text summarization, and highlighting the limitations of ROUGE score Open
The limited availability of datasets for text summarization tasks and their similar characteristics (e.g. news articles) make it crucial to focus on unsupervised learning techniques to enable summarization across different domains. Moreove…
Improving Sentiment Classification Using 0-Shot Generated Labels for Custom Transformer Embeddings Open
In this article, we present an approach to enrich transformers with additional information for general classification tasks given a set of relevant helper labels. We investigate whether the addition of preselected emotions as relevant help…
View article: 89 - Twelve-month Experience with Intravesical Botulinum Toxin Type A Administration Using Electromotive Drug Administration for Refractory Overactive Bladder
89 - Twelve-month Experience with Intravesical Botulinum Toxin Type A Administration Using Electromotive Drug Administration for Refractory Overactive Bladder Open
Hypothesis / aims of study: Overactive bladder (OAB) is a condition characterized by symptoms of urgency, frequency, and nocturia, often accompanied by urinary incontinence. For patients who do not respond to pharmacological therapies, bot…
Attention Visualizer Package: Revealing Word Importance for Deeper Insight into Encoder-Only Transformer Models Open
This report introduces the Attention Visualizer package, which is crafted to visually illustrate the significance of individual words in encoder-only transformer-based models. In contrast to other methods that center on tokens and self-att…
Efficient Latent Space Compression for Lightning-Fast Fine-Tuning and Inference of Transformer-Based Models Open
This paper presents a technique to reduce the number of parameters in a transformer-based encoder–decoder architecture by incorporating autoencoders. To discover the optimal compression, we trained different autoencoders on the embedding s…
Lottery Ticket Search on Untrained Models with Applied Lottery Sample Selection Open
In this paper, we present a new approach to improve tabular datasets by applying the lottery ticket hypothesis to tabular neural networks. Prior approaches were required to train the original large-sized model to find these lottery tickets…
Lottery Ticket Search on Untrained Models With Applied Lottery Sample Selection Open
In our recent paper [1] we presented leading results in tabular datasets by applying the lottery ticket hypothesis to tabular neural networks. However, we were required to train the original large-sized model to find these lottery tickets.…
Lottery Ticket Structured Node Pruning for Tabular Datasets Open
This paper experiments with well known pruning approaches, iterative and one-shot, and presents a new approach to lottery ticket pruning applied to tabular neural networks based on iterative pruning. Our contribution is a standard model fo…
Optimization and performance testing of a sequence processing pipeline applied to detection of nonindigenous species Open
Genetic taxonomic assignment can be more sensitive than morphological taxonomic assignment, particularly for small, cryptic or rare species. Sequence processing is essential to taxonomic assignment, but can also produce errors because opti…
An Individual-Based Modeling Approach to Investigate Sympatric Speciation via Specialized Resource Usage Open
An individual-based model, EcoSim, was employed to investigate if specialized resource use could promote sympatric speciation. Prey individuals in the original version of EcoSim were supplied with a single primary food resource. A dual res…