Procesamiento del Lenguaje Natural para determinar el grado de acierto o validez de una respuesta corta basado en palabras clave
Autor:
Sanz-Fayos, Javier
Fecha:
20/09/2021Palabra clave:
Tipo de Ítem:
masterThesis
Resumen:
En ocasiones, el contenido y calidad de un examen no se adecúa a los objetivos marcados
para la prueba. Por eso, se pretende desarrollar una herramienta capaz de reconocer las
respuestas de contenido más pobre, facilitando feedback al estudiante y/o al profesor. En
este trabajo, se estudia la influencia del reconocimiento de palabras clave como método
de evaluación semiautomático en relación a la calificación final de una respuesta. Para
ello, se elaboran técnicas de segmentación, lematización y desambiguación del sentido de
las palabras mediante un corpus seleccionado. Además de analizar palabras clave en la
respuesta pre-procesada del alumno, se estudian sus sinónimos y antónimos recogidos en
dos tesauros creados automáticamente. Los resultados obtenidos avalan el funcionamiento
del método desarrollado pero indican una falta de relación entre la técnica de evaluación
desarrollada y la real, evidenciando la falta de impacto de las palabras clave sobre la nota.
Descripción:
Sometimes, the content and quality of an exam does not match the objectives set for
the test. For this reason, it is intended to develop a tool capable of recognizing the answers
to the poorest content, providing feedback to the student and/or the teacher. In this work,
the influence of keyword recognition is studied as a semi-automatic evaluation method in
relation to the final rating of an answer. For achieving this, techniques of segmentation,
lemmatization and word sense disambiguation are developed through a selected corpus.
Not only keywords are analyzed in the student’s pre-processed response, their synonyms
and antonyms collected in two automatically created dictionaries are studied too. The
obtained results support the functioning of the developed method but also indicate a lack
of relationship between the developed evaluation technique and the real one, evidencing
the lack of impact that keywords have on the mark.
Ficheros en el ítem
Este ítem aparece en la(s) siguiente(s) colección(es)
Estadísticas de uso
| Año |
| 2012 |
| 2013 |
| 2014 |
| 2015 |
| 2016 |
| 2017 |
| 2018 |
| 2019 |
| 2020 |
| 2021 |
| 2022 |
| 2023 |
| 2024 |
| 2025 |
| Vistas |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 173 |
| 105 |
| 224 |
| 404 |
| Descargas |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 0 |
| 127 |
| 64 |
| 108 |
| 158 |
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Keyword-Based Processing for Assessing Short Answers in the Educational Field
Sanz-Fayos, Javier; de-la-Fuente-Valentín, Luis; Verdú, Elena (Communications in Computer and Information Science, 2022)When grading open-ended engineering exam responses, it is assessed to what extent its content and quality suit the requirements and accomplish the objectives of the test. This is a time consuming and subjective task. The ... -
Proposal of a Method for Analyzing the Explainability of Similarity Between Short Texts in Spanish
Jara Matas, Isidro; de-la-Fuente-Valentín, Luis; Ortega de la Puente, Alfonso; Sanz Fayos, Javier (Research.Publish.Connect, 2025)The aim of this project is the design and implementation of a system for analyzing the explainability of similarity between short texts (< 200 words), in Spanish language, with a special focus on the academic domain. For ... -
Relative Radiometric Normalization of Multitemporal images
Broncano Mateos, Carlos Javier; Pinilla Ruiz, Carlos; González-Crespo, Rubén; Castillo Sanz, Andrés G (International Journal of Interactive Multimedia and Artificial Intelligence (IJIMAI), 12/2010)A correct radiometric normalization between both images is fundamental for change detection. MAD method and its IR-MAD extension in an implementation on multisprectral aerial images is described in this paper.





