Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems
Math Word Problem (MWP) solving, which involves solving math problems in natural language, is a prevalent approach employed by Intelligent Tutoring Systems (ITS) for teaching mathematics. However, one major drawback of ITS is the complexity of encoding all potential solutions for each problem suppor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10167606/ |
| _version_ | 1797783580448915456 |
|---|---|
| author | Pablo Arnau-Gonzalez Ana Serrano-Mamolar Stamos Katsigiannis Turke Althobaiti Miguel Arevalillo-Herraez |
| author_facet | Pablo Arnau-Gonzalez Ana Serrano-Mamolar Stamos Katsigiannis Turke Althobaiti Miguel Arevalillo-Herraez |
| author_sort | Pablo Arnau-Gonzalez |
| collection | DOAJ |
| description | Math Word Problem (MWP) solving, which involves solving math problems in natural language, is a prevalent approach employed by Intelligent Tutoring Systems (ITS) for teaching mathematics. However, one major drawback of ITS is the complexity of encoding all potential solutions for each problem supported, which is both time-consuming and labour-intensive. In this study, we propose a novel method for automatically converting the statement of a previously unseen MWP into the internal representation of an ITS, thereby simplifying the task of adding new MWPs by only requiring the problem statement. To accomplish this, we propose the use of large pre-trained language models to translate the problem into Python code, which can then be easily imported into an ITS. Experimental results indicate that this approach is effective and suitable for the task, and as language models continue to improve, the accuracy rates are expected to increase further. |
| first_indexed | 2024-03-13T00:28:52Z |
| format | Article |
| id | doaj.art-3a9232bdb466464b8bcb958df0ee57d7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T00:28:52Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3a9232bdb466464b8bcb958df0ee57d72023-07-10T23:00:15ZengIEEEIEEE Access2169-35362023-01-0111670306703910.1109/ACCESS.2023.329047810167606Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring SystemsPablo Arnau-Gonzalez0https://orcid.org/0000-0001-9048-4659Ana Serrano-Mamolar1https://orcid.org/0000-0002-0027-7128Stamos Katsigiannis2https://orcid.org/0000-0001-9190-0941Turke Althobaiti3https://orcid.org/0000-0002-6674-7890Miguel Arevalillo-Herraez4https://orcid.org/0000-0002-0350-2079Departament d’Informática, Universitat de Valéncia, Burjassot, Valencia, SpainDepartamento de Lenguajes y Sistemas Informáticos, Universidad de Burgos, Burgos, SpainDepartment of Computer Science, Durham University, Durham, U.K.Faculty of Science, Northern Border University, Arar, Saudi ArabiaDepartament d’Informática, Universitat de Valéncia, Burjassot, Valencia, SpainMath Word Problem (MWP) solving, which involves solving math problems in natural language, is a prevalent approach employed by Intelligent Tutoring Systems (ITS) for teaching mathematics. However, one major drawback of ITS is the complexity of encoding all potential solutions for each problem supported, which is both time-consuming and labour-intensive. In this study, we propose a novel method for automatically converting the statement of a previously unseen MWP into the internal representation of an ITS, thereby simplifying the task of adding new MWPs by only requiring the problem statement. To accomplish this, we propose the use of large pre-trained language models to translate the problem into Python code, which can then be easily imported into an ITS. Experimental results indicate that this approach is effective and suitable for the task, and as language models continue to improve, the accuracy rates are expected to increase further.https://ieeexplore.ieee.org/document/10167606/Math word problemsalgebra tutoringintelligent tutoring systemsautomatic code generation |
| spellingShingle | Pablo Arnau-Gonzalez Ana Serrano-Mamolar Stamos Katsigiannis Turke Althobaiti Miguel Arevalillo-Herraez Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems IEEE Access Math word problems algebra tutoring intelligent tutoring systems automatic code generation |
| title | Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems |
| title_full | Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems |
| title_fullStr | Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems |
| title_full_unstemmed | Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems |
| title_short | Toward Automatic Tutoring of Math Word Problems in Intelligent Tutoring Systems |
| title_sort | toward automatic tutoring of math word problems in intelligent tutoring systems |
| topic | Math word problems algebra tutoring intelligent tutoring systems automatic code generation |
| url | https://ieeexplore.ieee.org/document/10167606/ |
| work_keys_str_mv | AT pabloarnaugonzalez towardautomatictutoringofmathwordproblemsinintelligenttutoringsystems AT anaserranomamolar towardautomatictutoringofmathwordproblemsinintelligenttutoringsystems AT stamoskatsigiannis towardautomatictutoringofmathwordproblemsinintelligenttutoringsystems AT turkealthobaiti towardautomatictutoringofmathwordproblemsinintelligenttutoringsystems AT miguelarevalilloherraez towardautomatictutoringofmathwordproblemsinintelligenttutoringsystems |