Research projects

EU projects

EHRI “European Holocaust Research Infrastructure”

EHRI “European Holocaust Research Infrastructure”

Digitalisation of the archival research on the Holocaust.

DARIAH

DARIAH

Digital Research Infrastructure for the Arts and Humanities.

CounteR

CounteR

Privacy-first situational awareness platform for violent terrorism and crime prediction, counter-radicalisation and citizen protection.

ATRIUM

ATRIUM

ATRIUM aims to empower Arts and Humanities scholars in their use of digital methods by facilitating access to a wide range of reusable workflows and interoperable, composable services offered by leading research infrastructures in the Arts and Humanities domain.

ANR projects

MaTOS

MaTOS

The MaTOS (Machine Translation for Open Science) project aims to develop new methods for the machine translation (MT) of complete scientific documents, as well as automatic metrics to evaluate the quality of these translations.

SINNet

SINNet

Socio-inspired Neural Networks.

TraLaLaM

TraLaLaM

Translating with large language models.

REVITALISE

REVITALISE

ViRtual bEhaVioral skIlls TrAining for pubLIc SpEaking.

Other national projects

Cap'FALC

Cap'FALC

Development of a text simplification algorithm and an accessible tool to ease the production of FALC (the French equivalent of “Easy read”).

NER4archives

NER4archives

Named entity recognition for finding aids in XML-EAD, a standard for encoding descriptive information regarding archival records.

EFL

EFL

Empirical foundations of linguistics, including computational linguistics and natural language processing.

LiLT

LiLT

Linguistic issues in language technology.

Huma-Num

Huma-Num

Very large research infrastructure (TGIR) aimed at facilitating the digitalisation of humanities and social sciences.

Matériaux Anciens et Patrimoniaux

Matériaux Anciens et Patrimoniaux

The Domaine d’intérêt majeur (DIM) Heritage and ancient materials is the Île-de-France research network dedicated to the study of ancient and patrimonial materials.

Patrimoines matériels – innovation, expérimentation et résilience

Patrimoines matériels – innovation, expérimentation et résilience

Nénufar

Nénufar

Digitalisation and exploitation of the early editions of the Petit Larousse dictionary.

DataCatalogue

DataCatalogue

Automatic extraction of sale catalogues logical structure.

OncoLab

OncoLab

Standardisation and structuring of cancer-related health data.

COLaF

COLaF

Resources and tools for languages of France.

TIERED

TIERED

Transforming Interdisciplinary Education and Research for Evolving Democracies.

HTRogène

HTRogène

Generalization of HTR models through the production of data for Romance languages and medieval manuscripts.

International projects

Universal Dependencies Project

Universal Dependencies Project

The Universal Dependencies project is an open community effort with over 300 contributors producing nearly 200 treebanks in over 100 languages.

Interpersonality

Interpersonality

Impact of personality on conversation, impact of conversational features on personality.

Past projects

EU projects
  • enCollect (COST, 2017-2020): Combining language learning and crowdsourcing for developing language teaching materials and more generic language resources for NLP.
  • DESIR (H2020, 2017-2019): The DESIR project aims at contributing to the sustainability of the DARIAH infrastructure along all its dimensions: dissemination, growth, technology, robustness, trust and education. Inria is responsable for providing of a portfolio of text analytics services based on GROBID and entity-fishing.
  • HIRMEOS (H2020, 2017-2019): Integration of Research Monographs in the European Open Science infrastructure.
  • Parthenos (H2020, 2015-2019): Strengthening the cohesion of research in the broad sector of Linguistic Studies, Humanities, Cultural Heritage, History, Archaeology and related fields through a thematic cluster of European Research Infrastructures, integrating initiatives, e-infrastructures and other world-class infrastructures, and building bridges between different, although tightly interrelated, fields.
  • Iperion CH (H2020, 2015-2019): Coordinating infrastructural activities in the cultural heritage domain.
ANR projects
  • BASNUM (ANR, 2018-2023): Digitalisation and computational annotation and exploitation of Henri Basnage de Beauval’s encyclopedic dictionary (1701).
  • Profiterole (ANR, 2017-2021): Modelling and analysis of Medieval French.
  • ParSiTi (ANR, 2016-2022): Context-aware parsing and machine translation of user-generated content.
  • TIME-US (ANR, 2016-2021): Digital study of remuneration and time budget textile trades in XVIIIth and XIXth century France.
  • SoSweet (ANR, 2015-2020): Studying sociolinguistic variability on Twitter, comparing linguistic and graph-based views on tweets.
  • PARSE-ME (ANR, 2015-2021): Multi-word expressions in parsing.
  • VerDI (ANR RAPID, 2015-2018): Automatic identification of information concealment on the internet.
Other national projects
  • HTRomance (BNF Datalab, 2023-2023): The HTRomance project is based on handwriting recognition (HTR). In particular, it proposes to evaluate and improve the capabilities of this technology when applied to literary manuscripts and public and private archives, in Latin and Romance languages, from the 11th to the 19th century, kept at the French National Library. The main objective of the project is the production of training data and transcription models resistant to changes in handwriting and language. It also intends to produce language models applicable to documents in ancient languages or to ancient language states. The development of training corpora will be accompanied and consolidated by the development and implementation of a novel process for evaluating the readability of output texts and the costs of producing new training data for HTR. HTRomance is complementary to editing or data mining projects: the models produced are likely to be used to obtain the textual data needed for editing or text mining.
  • DAdaNMT (Sorbonne Emergence, 2022-2023): The aim of this project is to investigate domain adaptation for neural machine translation. We will be exploring the adaptation of models to specific, low-resource domains domains as well as training models for multiple domains.
  • Gallic(orpor)a (BNF Datalab, 2021-2022): Consolidate and apply a processing chain for ancient Gallica documents in long diachrony, from the first French manuscripts to revolutionary prints.
  • PRAIRIE (3IA, 2019-2023): The PRAIRIE Institute (PaRis AI Research InstitutE) is one of the four French Institutes of Artificial Intelligence, which were created as part of the national French initiative on AI announced by President Emmanuel Macron on May 29, 2018. PRAIRIE’s objective is to become within five years a world leader in AI research and higher education, with an undeniable impact on economy and technology at the French, European and global levels. It brings together academic members (“PRAIRIE chairs”) who excel at research and education in both the core methodological areas and the interdisciplinary aspects of AI, and industrial members that are major actors in AI at the global level and a very strong group of international partners.
  • DAHN (Convention (MIC, Archives Nationales), 2019-2022): Digitalisation and computational exploitation of archives of historical interest.
  • LECTAUREP (Convention (MIC, Archives Nationales), 2018-2021): Development of a platform for the transcription, reading and automatic analysis of notarial deeds present in the National Archives.
  • OPALINe (PIA, 2017-2020): Development of tools for the accessibility of digital books for visually impaired people.
International projects
  • BigScience (Informal initiative, 2021-2022): This collaboration aims at fostering discussions and reflections around the research questions surrounding large language models (capabilities, limitations, potential improvements, bias, ethics, environmental impact, role in the general AI/cognitive research landscape) as well as the challenges around creating and sharing such models and datasets for research purposes and among the research community. The collaborative tasks involves creating, sharing and evaluating a large multilingual dataset and a large multilingual generative language model. An uncommonly large compute budget was allocated for these collaborative tasks (several millions GPU hours on several thousands GPUs, in particular on the French public cluster Jean Zay).
  • NLP Resources for Analyzing Reactions to Major Events in Hebrew and French Social Media (PHC Maïmonide, 2018-2019): Building NLP resources for analyzing reactions to major events in Hebrew and French social media.
  • MCM-NL (ANR-NSF, 2016-2020): Exploring correlations between data from neuro-imagery (fMRI, EEG) and data from NLP tools (mostly parsers). The data comes from “Le Petit Prince” read in French and English, and parsed with different parsers.