Optimization of state of the art techniques for Natural Language Understanding

Fabiano, Ariel Alejandro (2020). Optimization of state of the art techniques for Natural Language Understanding. Thesis (Master thesis), E.T.S. de Ingenieros Informáticos (UPM).

Description

Title: Optimization of state of the art techniques for Natural Language Understanding
Author/s:
  • Fabiano, Ariel Alejandro
Contributor/s:
  • Mateos Caballero, Alfonso
Item Type: Thesis (Master thesis)
Masters title: Inteligencia Artificial
Date: March 2020
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (5MB) | Preview

Abstract

One of the most complex challenges of Artificial Intelligence is to fully understand language the same way humans do. Natural Language Understanding is a field that has had some of the most groundbreaking innovations in the last years, yet is still far from having cognitive capabilities. The following work covers parts of the evolution of this field and uses a novel challenge proposed by Google as the problem to test how well these theories hold up to the task. Several techniques are tested up to state of the art standard and for the top performing model an extensive fine-tuning process is performed. As part of a competition held by Kaggle, the goal of this work will not only be a scientific study of these models, but a log of the process involving the creation of a model capable of achieving top performance.

More information

Item ID: 62939
DC Identifier: http://oa.upm.es/62939/
OAI Identifier: oai:oa.upm.es:62939
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 08 Jul 2020 08:57
Last Modified: 08 Jul 2020 08:57
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM