English

Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets

Computation and Language 2026-01-26 v2

Abstract

This paper presents a method for text simplification based on two neural architectures: a neural machine translation (NMT) model and a fine-tuned large language model (LLaMA). Given the scarcity of existing resources for Estonian, a new dataset was created by combining manually translated corpora with GPT-4.0-generated simplifications. OpenNMT was selected as a representative NMT-based system, while LLaMA was fine-tuned on the constructed dataset. Evaluation shows LLaMA outperforms OpenNMT in grammaticality, readability, and meaning preservation. These results underscore the effectiveness of large language models for text simplification in low-resource language settings. The complete dataset, fine-tuning scripts, and evaluation pipeline are provided in a publicly accessible supplementary package to support reproducibility and adaptation to other languages.

Keywords

Cite

@article{arxiv.2501.15624,
  title  = {Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets},
  author = {Eduard Barbu and Meeri-Ly Muru and Sten Marcus Malva},
  journal= {arXiv preprint arXiv:2501.15624},
  year   = {2026}
}

Comments

RANLP 2025 version, including code and data

R2 v1 2026-06-28T21:18:32.068Z