ANSWER (PI , GDN)
ANSWER stands for Advanced aNd SecuredWeb Experience and seaRch17. It is a GDN project (Grands Défis du Numérique) from the PIA program (Programme d’Investissements d’Avenir) on Big Data. The project is between four Inria research teams and the Qwant company.
The aim of the ANSWER project is to develop the new version of the Qwant18 search engine by introducing radical innovations in terms of search criteria as well as indexed content and users’ privacy. The purpose is to strengthen everyone’s confidence in the search engine and increase the effectiveness of Web search. Building trust in the search engine is based on innovations in (1) Security: computer security, privacy; (2) Completeness: completeness and heterogeneity of (re)sources; and (3) Neutrality: analysis, extraction, indexing, and classification of data.
Increasing the effectiveness of Web-based research relies on innovations related to (1) Relevance: variety and value of content taken into account, measurement of emotions carried by query results; (2) Interaction with the user: adaptation of the interfaces to the types of research; and (3) Performance: perceived relevance of results
and response time.
MONALIA 1.0 and 2.0
The MonaLIA 1.0 project is a preliminary study on the coupling of learning methods (Deep Neural Networks) and knowledge-based methods (Semantic Web) for image recognition and the enhancement of descriptive documentary records. The approach is applied and evaluated on the collection and data in the Joconde database in order to identify the possibilities and challenges offered by this coupling in assisting in the creation and maintenance of such an annotated collection. MonaLIA 2.0 will extend this work by proposing a complete prototype.
IADB, Integration and Learning on Biomedical Data, is a project funded by UCA JEDI Labex (Université Côte d’Azur). The goal of the project is to leverage medical prognosis and decision making in the clinical domain with big data analysis techniques, Natural Language Processing and Machine Learning. The partners are: I3S, Wimmics, CHU Nice and BCL (Bases, Corpus, Language) Laboratory.
INCERTIMMO, Uncertainty in Real Estate Spatial Modeling in the City, is a research and development
partnership funded by UCA and Kinaxia company. UCA partners are: I3S, ESPACE, and IMREDD.
SIDES 3.0 is an ANR project (2017-2020) which started in fall 2017. It is led by Université Grenoble Alpes (UGA) and its general objective is to introduce semantics within the existing SIDES educational platform for medicine students, in order to provide them with added value educational services.
Inria Federated Query Scaler
Federated Query Scaler is an Exploratory Research Project (PRE) funded by Inria, together with the Dyliss team at Inria Rennes. The topic of this project is the study of distributed SPARQL queries in the context of bioinformatics.
MIREL, MIning and REasoning with legal text, is a Research and Innovation Staff Exchange (RISE) project, funded by Marie Skłodowska-Curie grant, duration: 2016-2019. The MIREL project will create an international and inter-sectorial network to define a formal framework and to develop tools for MIning and REasoning with Legal texts, with the aim of translating these legal texts into formal representations that can be used for querying norms, compliance checking, and decision support. MIREL addresses both conceptual challenges, such as the role of legal interpretation in mining and reasoning, and computational challenges, such as the handling of big legal data, and the complexity of regulatory compliance. It bridges the gap between the community working on legal ontologies and NLP parsers and the community working on reasoning methods and formal logic. Moreover, it is the first project of its kind to involve industrial partners in the future development of innovative products and services in legal reasoning and their deployment in the market. MIREL promotes mobility and staff exchange between SMEs to academies in order to create an inter-continental interdisciplinary consortium in Law and Artificial Intelligence areas including Natural Language Processing, Computational Ontologies, Argumentation, and Logic & Reasoning.
The ANR project WASABI started in January 2017 with IRCAM, Deezer, Radio France and the SME Parisson, consists in building a 2 million songs knowledge base of commercial popular music (rock, pop, etc.) Its originality is the joint use of audio-based music information extraction algorithms, song lyrics analysis algorithms (natural language processing), and the use of the Semantic Web. Web Audio technologies then explore these bases of musical knowledge and provide innovative applications for composers, musicologists, music schools and sound engineers, music broadcasters and journalists (check for example these videos).
The theme of this new project with DGA is counter argumentation against fake news. Its duration is 2018-2020.
The goal of ALOOF is to enable robots to tap into the ever-growing amount of knowledge available on the Web, by learning from there about the meaning of previously unseen objects, expressed in a form that makes them applicable when acting in situated environments.
AZKAR is a two years french project funded by BPI (Banque Publique d’Investissement), focused on Fast Control of Mobile Robots over the Internet, using web technologies such as WebRTC and semantic web technologies. See this video.
In the SEEMPAD joint team we decided to focus on a very precise goal, i.e. generating, annotating and analyzing a dataset that documents a debate.
SMILK (Social Media Intelligence and Linked Knowledge) is a joint laboratory (Labcom, 2013-2016) between the WIMMICS team and the Research and Innovation unit of VISEO (Grenoble). Natural Language Processing, Linked Open Data and Social Networks as well as the links between them are at the core of this LabCom. The purpose of SMILK is both to develop research and technologies in order to retrieve, analyze, and reason on textual data coming from Web sources, and to make use of LOD, social networks structures and interaction in order to improve the analysis and understanding of textual resources.
Topics covered by SMILK include: use of data and vocabularies published on the web in order to search, analyze, disambiguate and structure textual knowledge in a smart way, but also to feed internal information sources; reasoning on the combination of internal and public data and schemes, query and presentation of data and inferences in natural formats.
Wimmics is awarded a software development grant for two years (2014-2015) from Inria to leverage Corese:
- W3C Recommendations RDF 1.1, RDFa
- Distributed Query Processing
- Graph Indexing
- Approximate Search and Semantic Distance
QAKiS is a system for open domain Question Answering over linked data. It addresses the problem of question interpretation as a relation-based match, where fragments of the question are matched to binary relations of the triple store, using relational textual patterns automatically collected. There is an online version of the system and a screencast of it too.
Discovery hub is an exploratory search engine which helps you to discover things you might like or be interested in. It widens your cultural and knowledge horizons by revealing and explaining unattended information. Based on Wikipedia data, Discovery Hub is cross-domain and works on numerous topics including music, cinema, literature but also politics, automobile and much more. It allows performing queries in an innovative way and helps you to navigate rich results. As a hub, it proposes redirections to others platforms to make you benefit from your discoveries (Youtube, Deezer and more). There are several recorded demos of Discovery Hub as well as an online public version (old version here).
ZONE-project provides a new, innovative way to follow news. At its core, the system is aggregating news items from various RSS feeds. Using the power of semantic web we are able to efficiently tag & annotate each news.Those tags are the basis of filters. Filters allow users to see only news that are relevant. For instance users can retrieve all news containing a tag, or on the contrary never see news containing specific tags. Basically it means that each user can create custom news feeds according to his interests. Though it may be tedious for John Doe to build its own filters, thus it will be possible to exchange filters with other users, or read specific news feeds built by other users. This will enable users to create news group feed focused on specific topics such as technology, heath, industry, transport, agriculture, communication, environment… No field can escape from the ZONE search and news feed mechanism!
Christophe DESCLAUX is currently working full time on this project thanks to Inria. In fact this project won the BoostYourCode 2012 contest which was created in order to promote free & open source software.
Design and Implementation of a version of DBPedia for Wikipedia in french, French Ministry of Culture.
CrEDIBLE is a project funded by the MASTODONS (Défi Grandes Masses de Données Scientifiques) projects of the CNRS Mission Interdisciplinarité. It aims at studying the scientific locks when constructing systems sharing distributed and heterogeneous data in the domain medical imaging.
The objective of OCKTOPUS ANR project is to increase the potential social and economic benefit of the large and quickly growing amounts of user-generated content, by transforming it into useful knowledge. We believe that it is possible to considerably improve upon existing generic Information Retrieval techniques by exploiting the specific structure of this content and of the online communities which produce it. Specifically, we will focus on a multi-disciplinary approach in order to address the problem of finding relevant answers to questions within forums and question-answer sites.
Development activity (ADT) with support from INRIA (2010-2012) on Semantic Graph Visualization providing the SemanticWebImport Gephi Plugin. The action focus is on coupling Corese and Gephi Open Graph Visualization Platform to provide a framework to query and visualize RDF data taking into account their schemas.
The Kolflow project (ANR project, 2011-2014) proposes to extend collective intelligence with smart agents relying on automated reasoning. Smart agents can significantly reduce the overhead of communities in the process of continuously building knowledge. Consequently, continuous knowledge building is much more effcient. Kolflow aims at building a social semantic space where humans collaborate with smart agents in order to produce knowledge understandable by humans and machines. Humans are able to understand the actions of smart agents. Smart agents are able to understand actions of humans. Kolflow targets the co-evolution of content and knowledge as the result of interactions of humans and machines.
DataLift (2010-2013) is an experimental research project funded by the ANR French national research agency. Its goal is to design a platform to publish and interlink datasets on the Web of data. Datalift will both publish datasets coming from a network of partners and data providers and propose a set of tools for easing the datasets publication process.
DataLift brings raw structured data coming from various formats (relational databases, CSV, XML, …) to semantic data interlinked on the Web of Data.
Isicil (2009-2012) this three year project proposes to study and to experiment with the usage of new tools to assist corporate intelligence tasks. These tools rely on web 2.0 advanced interfaces (blog, wiki, social bookmarking) for interactions and on semantic web technologies for interoperability and information processing. For more information see the description of the ISICIL project or contact the project leader Fabien Gandon.
Previous, bilateral collaborations
- Research and development collaboration with Mnemotix in particular on the outputs of the ISICIL project
- Alcatel Bell Lucent: PhD Thesis of Nicolas Marie on Pervasive sociality through social objects (2011-2013)
- SAP Research: PhD Thesis of Corentin Follenfant on Semantic Web and Business Intelligence (2011-2013)
- University Gaston Berger, Saint-Louis, Senegal: Semantic and Social Web Platform for Communities Knowledge Sharing, (accepted AUF project 2011-2013)
- University Badji Mokhtar, Annaba, Algérie: Personalization and socialization of e-learning systems based on semantic web models (CNRS/DPGRF project 2010-2012)
- CSTB: PhD of Khalil Riad Bouzidi on Modeling regulatory documents (2009-2012)
- IGN Cogit: Master Thesis on Semantics for Cartography (2011)
See also older projects in the Edelweiss research team.