Difficulty Estimation and Simplification of French Text Using LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jamet, Henri, Shrestha, Yash Raj, Vlachos, Michalis
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917733240668160
author Jamet, Henri
Shrestha, Yash Raj
Vlachos, Michalis
author_facet Jamet, Henri
Shrestha, Yash Raj
Vlachos, Michalis
contents We leverage generative large language models for language learning applications, focusing on estimating the difficulty of foreign language texts and simplifying them to lower difficulty levels. We frame both tasks as prediction problems and develop a difficulty classification model using labeled examples, transfer learning, and large language models, demonstrating superior accuracy compared to previous approaches. For simplification, we evaluate the trade-off between simplification quality and meaning preservation, comparing zero-shot and fine-tuned performances of large language models. We show that meaningful text simplifications can be obtained with limited fine-tuning. Our experiments are conducted on French texts, but our methods are language-agnostic and directly applicable to other foreign languages.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18061
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Difficulty Estimation and Simplification of French Text Using LLMs
Jamet, Henri
Shrestha, Yash Raj
Vlachos, Michalis
Computation and Language
Artificial Intelligence
We leverage generative large language models for language learning applications, focusing on estimating the difficulty of foreign language texts and simplifying them to lower difficulty levels. We frame both tasks as prediction problems and develop a difficulty classification model using labeled examples, transfer learning, and large language models, demonstrating superior accuracy compared to previous approaches. For simplification, we evaluate the trade-off between simplification quality and meaning preservation, comparing zero-shot and fine-tuned performances of large language models. We show that meaningful text simplifications can be obtained with limited fine-tuning. Our experiments are conducted on French texts, but our methods are language-agnostic and directly applicable to other foreign languages.
title Difficulty Estimation and Simplification of French Text Using LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.18061