activity
20242026
most citediText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CL2026

Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitexts

Antoine Taroni, Ludovic Moncla, Frederique Laforest

Efficient communication requires balancing informativity and simplicity when encoding meanings. The Information Bottleneck (IB) framework captures this trade-off formally, predicti…

cs.CL2026

EDDA-Coordinata: An Annotated Dataset of Historical Geographic Coordinates

Ludovic Moncla, Pierre Nugues, Thierry Joliveau +1

This paper introduces a dataset of enriched geographic coordinates retrieved from Diderot and d'Alembert's eighteenth-century Encyclopedie. Automatically recovering geographic coor…

cs.AI2025

ATOM: AdapTive and OptiMized dynamic temporal knowledge graph construction using LLMs

Yassir Lairgi, Ludovic Moncla, Khalid Benabdeslem +2

In today's rapidly expanding data landscape, knowledge extraction from unstructured text is vital for real-time analytics, temporal inference, and dynamic memory frameworks. Howeve…

cs.CL2025

Token and Span Classification for Entity Recognition in French Historical Encyclopedias

Ludovic Moncla, Hédi Zeghidi

Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities. This study…

cs.AI20241 cited

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

Yassir Lairgi, Ludovic Moncla, Rémy Cazabet +2

Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making…

cs.IR2024

Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language Models

Hédi Zeghidi, Ludovic Moncla

This paper evaluates Few-Shot Prompting with Large Language Models for Named Entity Recognition (NER). Traditional NER systems rely on extensive labeled datasets, which are costly…