Look-up in Google Scholar
Full metadata record
Ochoa Luna, Jose Eduardo
Vizcarra Aguilar, Gerson Waldyr
2021-11-02T16:39:39Z
2021-11-02T16:39:39Z
2020
1073514
https://hdl.handle.net/20.500.12590/16901
Paraphrasing is the action of expressing the idea of a sentence using different words. Paraphrase generation is an interesting and challenging task due mainly to three reasons: (1) The nature of the text is discrete, (2) it is difficult to modify a sentence slightly without changing the meaning, and (3) there are no accurate automatic metrics to evaluate the quality of a paraphrase. This problem has been addressed with several methods. Even so, neural network-based approaches have been tackling this task recently. This thesis presents a novel framework to solve the paraphrase generation problem in English. To do so, this work focuses and evaluates three aspects of a model, as the teaser figure shows. (a) Static input representations extracted from pre-trained language models. (b) Convolutional sequence to sequence models as our main architecture. (c) Hybrid loss function between maximum likelihood and adversarial REINFORCE, avoiding the computationally expensive Monte-Carlo search. We compare our best models with some baselines in the Quora question pairs dataset. The results show that our framework is competitive against the previous benchmarks. (es_PE)
Tesis (es_PE)
application/pdf (es_PE)
eng (es_PE)
Universidad Católica San Pablo (es_PE)
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)
Paraphrase generation (es_PE)
Input representations (es_PE)
Convolutional sequence to sequence (es_PE)
Adversarial training (es_PE)
An adversarial model for paraphrase generation (es_PE)
info:eu-repo/semantics/masterThesis (es_PE)
Universidad Católica San Pablo. Departamento de Ciencia de la Computación (es_PE)
Ciencia de la Computación (es_PE)
Maestría (es_PE)
Maestro en Ciencia de la Computación (es_PE)
PE (es_PE)
http://purl.org/pe-repo/ocde/ford#1.02.01 (es_PE)
Programa Profesional de Ciencia de la Computación (es_PE)
https://purl.org/pe-repo/renati/level#maestro (es_PE)
29738760
https://orcid.org/0000-0002-8979-3785 (es_PE)
70001862
611017 (es_PE)
Alex Jesús Cuadros Vargas (es_PE)
Eraldo Luíz Rezende Fernandes (es_PE)
Camilo Thorne Freundt (es_PE)
Hugo Alatrista Salas (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