Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them

Anum Afzal, Juraj Vladika, Daniel Braun, Florian Matthes

2023

Abstract

Large Language Models work quite well with general-purpose data and many tasks in Natural Language Processing. However, they show several limitations when used for a task such as domain-specific abstractive text summarization. This paper identifies three of those limitations as research problems in the context of abstractive text summarization: 1) Quadratic complexity of transformer-based models with respect to the input text length; 2) Model Hallucination, which is a model’s ability to generate factually incorrect text; and 3) Domain Shift, which happens when the distribution of the model’s training and test corpus is not the same. Along with a discussion of the open research questions, this paper also provides an assessment of existing state-of-the-art techniques relevant to domain-specific text summarization to address the research gaps.

Paper Citation

in Harvard Style

Afzal A., Vladika J., Braun D. and Matthes F. (2023). Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 682-689. DOI: 10.5220/0011744500003393

in Bibtex Style

@conference{icaart23,
author={Anum Afzal and Juraj Vladika and Daniel Braun and Florian Matthes},
title={Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={682-689},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011744500003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Challenges in Domain-Specific Abstractive Summarization and How to Overcome Them
SN - 978-989-758-623-1
AU - Afzal A.
AU - Vladika J.
AU - Braun D.
AU - Matthes F.
PY - 2023
SP - 682
EP - 689
DO - 10.5220/0011744500003393