Current Research Projects

KOGIA - CIFRE (2023-2026)

Large Language Models, Knowledge Graphs and Dynamic Graph Neural Networks for competitive intelligence
Project leaders: L. Moncla (LIRIS) and P. Cleau (Auvalie Innovation)
Consortium: LIRIS, Auvalie Innovation

ECoDA (10 k€) - Fédération Informatique de Lyon (2025-2026)

This inter-laboratory project revolves around two research objectives: 1. Automatic identification of knowledge domains and analysis of their evolution. 2. Construction of a geo-historical knowledge graph (involving spatial and temporal dimensions). These objectives will be applied to a corpus of texts composed of several editions of the Dictionnaire Universel François-Latin de Trévoux (DUFLT) published between 1704 and 1771.
Project leaders: L. Moncla (LIRIS) and J. Velcin (ERIC)
Consortium: LIRIS, ERIC, ICAR

PrepaEmadit (30 k€) - Univ. Lumière Lyon 2 (2024-2025)

PrepaEmadit aims to carry out preliminary research into the automatic processing of lexicographical data extracted from Trévoux’s Dictionnaire Universel François-Latin. The funds allocated will be used to acquire the annotated version of the 3rd edition (1743), to digitise the 7th edition (1743) in collaboration with the BnF and to organise a two-day workshop in Lyon.
Project leaders: D. Vigier (ICAR)
Consortium: ICAR, LIRIS, ERIC

Co-PrepaEmadit (9 k€) - LabEx ASLAN (2024-2025)

Co-PrepaEmadit aims to carry out preliminary research studies on the automatic processing of lexicographical data extracted from Trévoux’s Dictionnaire Universel François-Latin. This funding enables us to recruit three Master 2 students in computer science and digital humanities for 6-month internships.
Project leaders: D. Vigier (ICAR)
Consortium: ICAR, LIRIS, ERIC

Past Research Projects

GEODE (200 k€) - LabEx ASLAN (2020-2024)

GEODE studies the major changes in geographic discourses in French encyclopedias between 1751 (the publication date of the first volume of the Encyclopédie ou dictionnaire raisonné des sciences, des arts et des métiers) and today (Wikipedia-France, 2018). The corpus will include not only these two encyclopedias, but also La Grande Encyclopédie (1885-1902), the Encyclopædia Universalis (2018). Each of these works constitutes a major step in the editorial history of encyclopedic publications in France since the Enlightenment. Our approach is resolutely interdisciplinary, including experts from linguistics, geographic information retrieval, computational linguistics, geography, history and digital humanities.
Project leaders: L. Moncla (LIRIS) and D. Vigier (ICAR)
Consortium: LIRIS, ICAR, EVS, LLF, LIDILEM

ESTD (7 k€) - Fédération Informatique de Lyon (2023-2024)

The project deals with the spatio-temporal study of discourse, in two independent (and multilingual: French/English) corpora. The objective is to develop and experiment methods to answer the following questions: How to characterize discourse in general? How to measure and interpret temporal evolutions in the characteristics of discourse? How to spatialize the results obtained?
Project leaders: L. Moncla (LIRIS) and A. Guille (ERIC)
Consortium: LIRIS, ERIC

CHOUCAS - ANR project (2017-2021)

Integration of heterogeneous data and spatial reasoning for assistance in locating victims in mountains. The project CHOUCAS is interdisciplinary involving researchers in geographic information sciences, computer science and natural language processing. The aim of the project is to provide methods and tools for enriching, structuring, querying and visualising spatial data coming from heterogeneous sources and reasoning to help the rescue teams to speed up the phase of victims location and to better estimate a probable location area.
Project leader: A.-M. Olteanu-Raimond (LaSTIG)
Consortium: LaSTIG, LMAP, LIG, PGHM de Grenoble

CARTIE (3 k€) - LabEx ASLAN (2021-2021)

This project will be part of an interdisciplinary collaboration (computer science, linguistics and geography) whose objective is the development of methods for text classification and representation of information. This exploratory project is upstream of the work that will be carried out in the GEODE (2020-2024) project funded by LabEx ASLAN, the main objective of which is a diachronic study of geographical discourse within French encyclopedias.
Project leader: L. Moncla (LIRIS) and D. Vigier (ICAR)
Consortium: LIRIS, ICAR

HExtGEO (54 k€) - IDEX Lyon Impulsion (2019-2020)

This project aims to design a software platform integrating different methods of the field of artificial intelligence combining NLP and Data Mining for the processing and analysis of geographic information. This project will strengthen interdisciplinary collaborations and federate research in engineering (computer science, data science) and social sciences (geography, history) around digital and societal issues related to the territory and the exploitation of textual data.
Project leader: L. Moncla (LIRIS)
Consortium: LIRIS

GéoDisco - MSH Lyon St-Etienne (2019-2020)

Géodisco combines GIS, NLP, textometry and discourse analysis around the same question: “What geographical representations of the world do French encyclopedias convey through their discourses, and what do these representations tell us about the time when these encyclopedias were written and published? This project is part of a network of national and international collaborations around encyclopedias and dictionaries.
Project leader: D. Vigier (ICAR)
Consortium: ICAR, LIRIS, EVS

HIL - LabEx IMU (2017-2020)

The aim of the project is to improve the spatial recommendation procedures by proposing neighbourhoods to people seeking housing. It consists of two parts. The first concerns the analysis and categorisation of neighbourhoods through a multidisciplinary perspective. Based on existing data, this involves producing an original typology of neighbourhoods in the Lyon conurbation and formalising these results and selected indicators in a computer model. The second part concerns the recommendation itself, with the aim of developing a method for matching the types of neighbourhood and the profiles of purchasers using the Home in Love platform.
Project leaders: L. Bonneval (CMW) and F. Favetta (LIRIS)
Consortium: CMW, LIRIS, Home in Love

YACA - Interreg Aquitaine-Aragon (2015-2017)

Open Source implementation of the multilingual processing chain for recognition, disambiguation and geocoding of place names from hiking descriptions.
Project leader: M. Gaio (LIUPPA)
Consortium: LIUPPA, IAAA

PERDIDO - CDAPP-IGN (2012-2015)

Project for extracting and retrieving displacements from textual documents. The main objective is the automatic geocoding of itineraries described in natural language. The work is divided into two main tasks. The first task aims at identifying and extracting information describing the itinerary in texts such as spatial named entities and expressions of displacement or perception. The second task deals with the reconstruction of the itinerary.
Project leader: M. Gaio (LIUPPA)
Consortium: LIUPPA, IAAA, COGIT IGN