Look-up in Google Scholar
Full metadata record
Ochoa Luna, Jose Eduardo
Muroya Lei, Stefanie
2021-09-15T01:23:27Z
2021-09-15T01:23:27Z
2021-09-15T01:23:27Z
2021-09-15T01:23:27Z
2021
1073395
https://hdl.handle.net/20.500.12590/16844
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 ane functions are the basis of most Artificial Intelligence (AI) models, this method can be applied to more complex architectures in the future. (es_PE)
Tesis (es_PE)
application/pdf (es_PE)
eng (es_PE)
Universidad Católica San Pablo (es_PE)
SUNEDU
info:eu-repo/semantics/openAccess (es_PE)
https://creativecommons.org/licenses/by/4.0/ (es_PE)
Universidad Católica San Pablo (es_PE)
Repositorio Institucional - UCSP (es_PE)
reponame:UCSP-Institucional
instname:Universidad Católica San Pablo
instacron:UCSP
Quantum Annealing (es_PE)
ISING Model (es_PE)
Sampling (es_PE)
Natural Language Processing (es_PE)
Seq2Seq (es_PE)
Quantum exordium for natural language processing: A novel approach to sample on decoders (es_PE)
info:eu-repo/semantics/bachelorThesis (es_PE)
Universidad Católica San Pablo. Departamento de Ciencia de la Computación (es_PE)
Ciencia de la Computación (es_PE)
Título Profesional (es_PE)
Licenciado en Ciencia de la Computación (es_PE)
PE (es_PE)
http://purl.org/pe-repo/ocde/ford#1.02.01 (es_PE)
https://purl.org/pe-repo/renati/level#tituloProfesional (es_PE)
29738760
https://orcid.org/0000-0002-8979-3785 (es_PE)
76923844
611016 (es_PE)
Yván Jesús Túpac Valdivia (es_PE)
Julio Omar Santisteban Pablo (es_PE)
https://purl.org/pe-repo/renati/type#tesis (es_PE)
Privada asociativa
info:eu-repo/semantics/publishedVersion (es_PE)



This item is licensed under a Creative Commons License Creative Commons