Abstract
This paper describes multi-lingual long document summarization systems submitted to the Financial Narrative Summarization Shared Task (FNS 2022 ) by Team-Tredence. We developed task-specific summarization methods for 3 languages – English, Spanish and Greek. The solution is divided into two parts, where a RoBERTa model was finetuned to identify/extract summarizing segments from English documents and T5 based models were used for summarizing Spanish and Greek documents. A purely extractive approach was applied to summarize English documents using data-specific heuristics. An mT5 model was fine-tuned to identify potential narrative sections for Greek and Spanish, followed by finetuning mT5 and T5(Spanish version) for abstractive summarization task. This system also features a novel approach for generating summarization training dataset using long document segmentation and the semantic similarity across segments. We also introduce an N-gram variability score to select sub-segments for generating more diverse and informative summaries from long documents.- Anthology ID:
- 2022.fnp-1.18
- 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:
- 112–115
- Language:
- URL:
- https://aclanthology.org/2022.fnp-1.18
- DOI:
- Cite (ACL):
- Manish Pant and Ankush Chopra. 2022. Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022. In Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022, pages 112–115, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Multilingual Financial Documentation Summarization by Team_Tredence for FNS2022 (Pant & Chopra, FNP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.fnp-1.18.pdf