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