Bibliographic citations
This is an automatically generated citacion. Modify it if you see fit
Muroya, S., (2021). Quantum exordium for natural language processing: a novel approach to sample on decoders [Trabajo de investigación, Universidad Católica San Pablo]. https://hdl.handle.net/20.500.12590/16617
Muroya, S., Quantum exordium for natural language processing: a novel approach to sample on decoders [Trabajo de investigación]. PE: Universidad Católica San Pablo; 2021. https://hdl.handle.net/20.500.12590/16617
@misc{renati/86354,
title = "Quantum exordium for natural language processing: a novel approach to sample on decoders",
author = "Muroya Lei, Stefanie",
publisher = "Universidad Católica San Pablo",
year = "2021"
}
Title: Quantum exordium for natural language processing: a novel approach to sample on decoders
Authors(s): Muroya Lei, Stefanie
Advisor(s): Ochoa Luna, Jose Eduardo
Keywords: Quantum Annealing; ISING Model; Sampling; Natural Language Processing; Seq2Seq
OCDE field: http://purl.org/pe-repo/ocde/ford#1.02.01
Issue Date: 2021
Institution: Universidad Católica San Pablo
Abstract: 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.
Link to repository: https://hdl.handle.net/20.500.12590/16617
Discipline: Ciencia de la Computación
Grade or title grantor: Universidad Católica San Pablo. Departamento de Ciencia de la Computación
Grade or title: Bachiller en Ciencia de la Computación
Juror: Alex Jesús Cuadros Vargas; Juan Carlos Gutiérrez Cáceres
Register date: 23-Feb-2021
This item is licensed under a Creative Commons License