Implementing Open-Domain Question-Answering in a College Setting: An End-to-End Methodology and a Preliminary Exploration

Augusto Gonzalez-Bonorino, Augusto Gonzalez-Bonorino, Eitel Lauría, Edward Presutti

2022

Abstract

Advances in Artificial Intelligence and Natural Language Processing (NLP) can be leveraged by higher-ed administrators to augment information-driven support services. But due to the incredibly rapid innovation rate in the field, it is challenging to develop and implement state-of-the-art systems in such institutions. This work describes an end-to-end methodology that educational institutions can utilize as a roadmap to implement open domain question-answering (ODQA) to develop their own intelligent assistants on their online platforms. We show that applying a retriever-reader framework composed of an information retrieval component that encodes sparse document vectors, and a reader component based on BERT -Bidirectional Encoder Representations from Transformers- fine-tuned with domain specific data, provides a robust, easy-to-implement architecture for ODQA. Experiments are carried out using variations of BERT fine-tuned with a corpus of questions and answers derived from our institution’s website.

Paper Citation

in Harvard Style

Gonzalez-Bonorino A., Lauría E. and Presutti E. (2022). Implementing Open-Domain Question-Answering in a College Setting: An End-to-End Methodology and a Preliminary Exploration. In Proceedings of the 14th International Conference on Computer Supported Education - Volume 2: CSEDU, ISBN 978-989-758-562-3, pages 66-75. DOI: 10.5220/0011059000003182

in Bibtex Style

@conference{csedu22,
author={Augusto Gonzalez-Bonorino and Eitel Lauría and Edward Presutti},
title={Implementing Open-Domain Question-Answering in a College Setting: An End-to-End Methodology and a Preliminary Exploration},
booktitle={Proceedings of the 14th International Conference on Computer Supported Education - Volume 2: CSEDU,},
year={2022},
pages={66-75},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011059000003182},
isbn={978-989-758-562-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Computer Supported Education - Volume 2: CSEDU,
TI - Implementing Open-Domain Question-Answering in a College Setting: An End-to-End Methodology and a Preliminary Exploration
SN - 978-989-758-562-3
AU - Gonzalez-Bonorino A.
AU - Lauría E.
AU - Presutti E.
PY - 2022
SP - 66
EP - 75
DO - 10.5220/0011059000003182