Transformer-based Models for Long Document Summarisation in Financial Domain

Urvashi Khanna, Samira Ghodratnama, Diego Moll ́a, Amin Beheshti


Abstract
Summarisation of long financial documents is a challenging task due to the lack of large-scale datasets and the need for domain knowledge experts to create human-written summaries. Traditional summarisation approaches that generate a summary based on the content cannot produce summaries comparable to human-written ones and thus are rarely used in practice. In this work, we use the Longformer-Encoder-Decoder (LED) model to handle long financial reports. We describe our experiments and participating systems in the financial narrative summarisation shared task. Multi-stage fine-tuning helps the model generalise better on niche domains and avoids the problem of catastrophic forgetting. We further investigate the effect of the staged fine-tuning approach on the FNS dataset. Our systems achieved promising results in terms of ROUGE scores on the validation dataset.
Anthology ID:
2022.fnp-1.10
Volume:
Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Mahmoud El-Haj, Paul Rayson, Nadhem Zmandar
Venue:
FNP
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
73–78
Language:
URL:
https://aclanthology.org/2022.fnp-1.10
DOI:
Bibkey:
Cite (ACL):
Urvashi Khanna, Samira Ghodratnama, Diego Moll ́a, and Amin Beheshti. 2022. Transformer-based Models for Long Document Summarisation in Financial Domain. In Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022, pages 73–78, Marseille, France. European Language Resources Association.
Cite (Informal):
Transformer-based Models for Long Document Summarisation in Financial Domain (Khanna et al., FNP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.fnp-1.10.pdf