Extractive Summarization System for Annual Reports

Abderrahim Ait Azzi, Juyeon Kang


Abstract
In this paper, we report on our experiments in building a summarization system for generating summaries from annual reports. We adopt an “extractive” summarization approach in our hybrid system combining neural networks and rules-based algorithms with the expectation that such a system may capture key sentences or paragraphs from the data. A rules-based TOC (Table Of Contents) extraction and a binary classifier of narrative section titles are main components of our system allowing to identify narrative sections and best candidates for extracting final summaries. As result, we propose one to three summaries per document according to the classification score of narrative section titles.
Anthology ID:
2020.fnp-1.24
Volume:
Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
FNP
SIG:
Publisher:
COLING
Note:
Pages:
143–147
Language:
URL:
https://aclanthology.org/2020.fnp-1.24
DOI:
Bibkey:
Cite (ACL):
Abderrahim Ait Azzi and Juyeon Kang. 2020. Extractive Summarization System for Annual Reports. In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pages 143–147, Barcelona, Spain (Online). COLING.
Cite (Informal):
Extractive Summarization System for Annual Reports (Ait Azzi & Kang, FNP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2020.fnp-1.24.pdf