Publication
NLP/AI based techniques for programming exercises generation
| dc.contributor.author | Freitas, Tiago | |
| dc.contributor.author | Neto, Álvaro | |
| dc.contributor.author | Pereira, Maria João | |
| dc.contributor.author | Henriques, Pedro | |
| dc.date.accessioned | 2023-09-21T14:38:34Z | |
| dc.date.available | 2023-09-21T14:38:34Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | This paper focuses on the enhancement of computer programming exercises generation to the benefit of both students and teachers. By exploring Natural Language Processing (NLP) and Machine Learning (ML) methods for automatic generation of text and source code, it is possible to semiautomatically construct programming exercises, aiding teachers to reduce redundant work and more easily apply active learning methodologies. This would not only allow them to still play a leading role in the teaching-learning process, but also provide students a better and more interactive learning experience. If embedded in a widely accessible website, an exercises generator with these Artificial Intelligence (AI) methods might be used directly by students, in order to obtain randomised lists of exercises for their own study, at their own time. The emergence of new and increasingly powerful technologies, such as the ones utilised by ChatGPT, raises the discussion about their use for exercise generation. Albeit highly capable, monetary and computational costs are still obstacles for wider adoption, as well as the possibility of incorrect results. This paper describes the characteristics and behaviour of several ML models applied and trained for text and code generation and their use to generate computer programming exercises. Finally, an analysis based on correctness and coherence of the resulting exercise statements and complementary source codes generated/produced is presented, and the role that this type of technology can play in a programming exercise automatic generation system is discussed. | pt_PT |
| dc.description.sponsorship | This work has been supported by FCT – Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020 and UIDB/05757/2020. | |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.citation | Freitas, Tiago; Neto, Álvaro; Pereira, Maria João; Henriques, Pedro (2023). NLP/AI based techniques for programming exercises generation. In 4th International Computer Programming Education Conference (ICPEC 2023). Vila do Conde. p. 1-12. ISBN 978-395977290-7 | pt_PT |
| dc.identifier.doi | 10.4230/OASIcs.ICPEC.2023.9 | pt_PT |
| dc.identifier.isbn | 978-3-95977-290-7 | |
| dc.identifier.issn | 2190-6807 | |
| dc.identifier.uri | http://hdl.handle.net/10198/28750 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.relation | ALGORITMI Research Center | |
| dc.relation | Research Centre in Digitalization and Intelligent Robotics | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Natural language processing | pt_PT |
| dc.subject | Computer programming education | pt_PT |
| dc.subject | Exercise generation | pt_PT |
| dc.subject | Text generation | pt_PT |
| dc.subject | Code generation | pt_PT |
| dc.title | NLP/AI based techniques for programming exercises generation | pt_PT |
| dc.type | conference paper | |
| dspace.entity.type | Publication | |
| oaire.awardTitle | ALGORITMI Research Center | |
| oaire.awardTitle | Research Centre in Digitalization and Intelligent Robotics | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00319%2F2020/PT | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05757%2F2020/PT | |
| oaire.citation.conferencePlace | Vila do Conde | pt_PT |
| oaire.citation.title | 4th International Computer Programming Education Conference (ICPEC 2023) | pt_PT |
| oaire.citation.volume | 112 | pt_PT |
| oaire.fundingStream | 6817 - DCRRNI ID | |
| oaire.fundingStream | 6817 - DCRRNI ID | |
| person.familyName | Pereira | |
| person.givenName | Maria João | |
| person.identifier.ciencia-id | C912-4A49-A3B3 | |
| person.identifier.orcid | 0000-0001-6323-0071 | |
| person.identifier.rid | G-5999-2011 | |
| person.identifier.scopus-author-id | 13907870300 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | conferenceObject | pt_PT |
| relation.isAuthorOfPublication | a20ccfa6-4e84-4c25-ab0d-8d6ba196ffc2 | |
| relation.isAuthorOfPublication.latestForDiscovery | a20ccfa6-4e84-4c25-ab0d-8d6ba196ffc2 | |
| relation.isProjectOfPublication | 0d98f999-8fd3-46a8-8a71-a7ff478a1207 | |
| relation.isProjectOfPublication | 6e01ddc8-6a82-4131-bca6-84789fa234bd | |
| relation.isProjectOfPublication.latestForDiscovery | 0d98f999-8fd3-46a8-8a71-a7ff478a1207 |