Nakanyseth Vuth
2025
“POPCORN-RENS : un nouveau jeu de données en français annoté en entités d’intérêts sur une thématique "“sécurité et défense”""
Lucas Aubertin
|
Guillaume Gadek
|
Gilles Sérasset
|
Maxime Prieur
|
Nakanyseth Vuth
|
Bruno Grilheres
|
Didier Schwab
|
Cédric Lopez
Actes de l'atelier Évaluation des modèles génératifs (LLM) et challenge 2025 (EvalLLM)
2024
KGAST: From Knowledge Graphs to Annotated Synthetic Texts
Nakanyseth Vuth
|
Gilles Sérasset
|
Didier Schwab
Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024)
In recent years, the use of synthetic data, either as a complement or a substitute for original data, has emerged as a solution to challenges such as data scarcity and security risks. This paper is an initial attempt to automatically generate such data for Information Extraction tasks. We accomplished this by developing a novel synthetic data generation framework called KGAST, which leverages Knowledge Graphs and Large Language Models. In our preliminary study, we conducted simple experiments to generate synthetic versions of two datasets—a French security defense dataset and an English general domain dataset, after which we evaluated them both intrinsically and extrinsically. The results indicated that synthetic data can effectively complement original data, improving the performance of models on classes with limited training samples. This highlights KGAST’s potential as a tool for generating synthetic data for Information Extraction tasks.
2023
DBnary2Vec: Preliminary Study on Lexical Embeddings for Downstream NLP Tasks
Nakanyseth Vuth
|
Gilles Sérasset
Proceedings of the 4th Conference on Language, Data and Knowledge
Search
Fix author
Co-authors
- Gilles Sérasset 3
- Didier Schwab 2
- Lucas Aubertin 1
- Guillaume Gadek 1
- Bruno Grilheres 1
- show all...