A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
This paper benchmarks various transformer-based summarization methods on long UK financial annual reports, critiques existing evaluation metrics, and proposes a novel BRUGEscore (the harmonic mean of ROUGE-2 and BERTscore) to better assess summarization quality, supported by statistical significance and adversarial robustness tests.
Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.