Comparing Approaches to Automatic Summarization in Less-Resourced Languages
It addresses the problem of limited summarization tools for less-resourced languages, but the approach is incremental as it primarily compares existing methods without introducing new paradigms.
This work compared various approaches to automatic text summarization in less-resourced languages, finding that a multilingual fine-tuned mT5 baseline generally outperformed other methods, including zero-shot LLMs, across most evaluation metrics.
Automatic text summarization has achieved high performance in high-resourced languages like English, but comparatively less attention has been given to summarization in less-resourced languages. This work compares a variety of different approaches to summarization from zero-shot prompting of LLMs large and small to fine-tuning smaller models like mT5 with and without three data augmentation approaches and multilingual transfer. We also explore an LLM translation pipeline approach, translating from the source language to English, summarizing and translating back. Evaluating with five different metrics, we find that there is variation across LLMs in their performance across similar parameter sizes, that our multilingual fine-tuned mT5 baseline outperforms most other approaches including zero-shot LLM performance for most metrics, and that LLM as judge may be less reliable on less-resourced languages.