RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents

Sayantan Adak, Animesh Mukherjee


Abstract
Inspirational quotes from famous individuals are often used to convey thoughts in news articles, essays, and everyday conversations. In this paper, we propose a novel context-based quote extraction system that aims to predict the most relevant quote from a long text. We formulate this quote extraction as an open domain question answering problem first by employing a vector-store based retriever and then applying a multi-task reader. We curate three context-based quote extraction dataset and introduce a novel multi-task framework RA-MTR that improves the state-of-the-art performance, achieving a maximum improvement of 5.08% in BoW F1-score.
Anthology ID:
2025.coling-main.365
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5443–5462
Language:
URL:
https://aclanthology.org/2025.coling-main.365/
DOI:
Bibkey:
Cite (ACL):
Sayantan Adak and Animesh Mukherjee. 2025. RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5443–5462, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents (Adak & Mukherjee, COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.365.pdf