Buscar en Google Scholar
Título: Quantum exordium for natural language processing: a novel approach to sample on decoders
Asesor(es): Ochoa Luna, Jose Eduardo
Campo OCDE: http://purl.org/pe-repo/ocde/ford#1.02.01
Fecha de publicación: 2021
Institución: Universidad Católica San Pablo
Resumen: The sampling task of Seq2Seq models in Natural Language Processing (NLP) is based on heuristics because of the Non-Deterministic Polynomial Time (NP) nature of this problem. The goal of this research is to develop a quantum sampler for Seq2Seq models, and give evidence that Quantum Annealing (QA) can guide the search space of these samplers. The contribution of this work is given by showing an architecture to represent Recurrent Neural Networks (RNN) in a quantum computer to finally develop a quantum sampler. The individual architectures (i.e. summation, multiplication, argmax, and activation functions) achieve optimal accuracies in both simulated and quantum environments. While the results of the overall proposal show that it can either outperform or match greedy approaches. As the very first steps of quantum NLP, these are tested against simple RNN with a synthetic data set of random numbers, and a real quantum computer is utilized. Since affine functions are the basis of most Artificial Intelligence (AI) models, this method can be applied to more complex architectures in the future.
Disciplina académico-profesional: Ciencia de la Computación
Institución que otorga el grado o título: Universidad Católica San Pablo. Departamento de Ciencia de la Computación
Grado o título: Bachiller en Ciencia de la Computación
Jurado: Alex Jesús Cuadros Vargas; Juan Carlos Gutiérrez Cáceres
Fecha de registro: 23-feb-2021; 23-feb-2021



Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons