In EDS ansehen

Question answering on introductory Java programming concepts using the Transformer ; Frågebesvarande för introduktionskurser i Java-programmering med hjälp av Transformermodellen

Gespeichert in:
Bibliographische Detailangaben
Titel: Question answering on introductory Java programming concepts using the Transformer ; Frågebesvarande för introduktionskurser i Java-programmering med hjälp av Transformermodellen
Autoren: Szerszen, Lukas
Verlagsinformationen: KTH, Skolan för elektroteknik och datavetenskap (EECS)
Publikationsjahr: 2021
Bestand: Royal Inst. of Technology, Stockholm (KTH): Publication Database DiVA
Schlagwörter: Computer and Information Sciences, Data- och informationsvetenskap
Beschreibung: AI applications for education could help students learn in their introductory programming courses. Many applications for education try to simulate a humantutoring session that engages the student in a dialogue. During the session, they can ask questions and have them answered while working throughan exercise. Refining the question-answering capability of such applicationsmay prove to be a base for supplementary education tools. These could be usedby students in introductory programming courses to ask questions to reviewconcepts in programming, facilitating the teaching done by professors. This thesis investigates question-answering on introductory Java programming using The Transformer model. The focus is on the extent to which the model can answer questions on Java concepts when trained on questions and answers from the online programming forum Stack Overflow. A total of five Transformer models with default parameters were trained on posts segmented with different granularities using byte-pair encoding. Each model was evaluated using perplexity as an automatic metric and a qualitative evaluation done by the author. The automatic metric evaluation scores a low perplexity indicating a hig hquality model. However, the qualitative evaluation shows that the generated responses are short, generic, repetitive, and even contradicting, with the most common response being “You can do it like this:“. That is, the model exhibits a fundamental inability to answers questions on Java programming concepts. ; AI-applikationer skulle kunde användas inom utbildning för att hjälpa studenter med deras inlärning i introduktionskurser i programmering. Många applikationer med utbildningssyfte försöker att simulera en mänsklig utbildningsmiljö där studenten i en dialog kan ställa frågor samt få dem besvarade i sambandmed att studenten arbetar med övningsuppgifter. Att förbättra förmågan hos denna sortens applikationer att besvara frågor skulle kunna utgöra en basför kompletterande utbildningsmaterial. Dessa applikationer skulle kunna ...
Publikationsart: bachelor thesis
Dateibeschreibung: application/pdf
Sprache: English
Relation: TRITA-EECS-EX; 2021:75
Verfügbarkeit: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-292201
Rights: info:eu-repo/semantics/openAccess
Dokumentencode: edsbas.BF1F001E
Datenbank: BASE
Beschreibung
Abstract:AI applications for education could help students learn in their introductory programming courses. Many applications for education try to simulate a humantutoring session that engages the student in a dialogue. During the session, they can ask questions and have them answered while working throughan exercise. Refining the question-answering capability of such applicationsmay prove to be a base for supplementary education tools. These could be usedby students in introductory programming courses to ask questions to reviewconcepts in programming, facilitating the teaching done by professors. This thesis investigates question-answering on introductory Java programming using The Transformer model. The focus is on the extent to which the model can answer questions on Java concepts when trained on questions and answers from the online programming forum Stack Overflow. A total of five Transformer models with default parameters were trained on posts segmented with different granularities using byte-pair encoding. Each model was evaluated using perplexity as an automatic metric and a qualitative evaluation done by the author. The automatic metric evaluation scores a low perplexity indicating a hig hquality model. However, the qualitative evaluation shows that the generated responses are short, generic, repetitive, and even contradicting, with the most common response being “You can do it like this:“. That is, the model exhibits a fundamental inability to answers questions on Java programming concepts. ; AI-applikationer skulle kunde användas inom utbildning för att hjälpa studenter med deras inlärning i introduktionskurser i programmering. Många applikationer med utbildningssyfte försöker att simulera en mänsklig utbildningsmiljö där studenten i en dialog kan ställa frågor samt få dem besvarade i sambandmed att studenten arbetar med övningsuppgifter. Att förbättra förmågan hos denna sortens applikationer att besvara frågor skulle kunna utgöra en basför kompletterande utbildningsmaterial. Dessa applikationer skulle kunna ...