iTA: A Digital Teaching Assistant

Vishnu Duggirala, Rhys Butler, Farnoush Banaei-Kashani

Abstract

Designed and implemented a question-answering chatbot, dubbed iTA (intelligent Teaching Assistant), which can provide detailed answers to questions by effectively identifying the most relevant answers in “long” text sources (documents or textbooks). iTA answers questions by implementing a two-stage procedure. First, the topmost relevant paragraphs are identified in the selected text source using a retrieval-based approach and scores for the retrieved paragraphs are computed. Second, using a generative model, extracted the relevant content from the top-ranked paragraph to generate the answer. Our results show that iTA is well suited to generate meaningful answers for questions posed by students.

Download


Paper Citation


in Harvard Style

Duggirala V., Butler R. and Banaei-Kashani F. (2021). iTA: A Digital Teaching Assistant. In Proceedings of the 13th International Conference on Computer Supported Education - Volume 2: CSEDU, ISBN 978-989-758-502-9, pages 274-281. DOI: 10.5220/0010461002740281


in Bibtex Style

@conference{csedu21,
author={Vishnu Duggirala and Rhys Butler and Farnoush Banaei-Kashani},
title={iTA: A Digital Teaching Assistant},
booktitle={Proceedings of the 13th International Conference on Computer Supported Education - Volume 2: CSEDU,},
year={2021},
pages={274-281},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010461002740281},
isbn={978-989-758-502-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Computer Supported Education - Volume 2: CSEDU,
TI - iTA: A Digital Teaching Assistant
SN - 978-989-758-502-9
AU - Duggirala V.
AU - Butler R.
AU - Banaei-Kashani F.
PY - 2021
SP - 274
EP - 281
DO - 10.5220/0010461002740281