By browsing our site you accept the installation and use cookies on your computer. Know more

Menu Logo Principal

Scientific documents annotation with @Web


All news

New publication: Xart: Discovery of correlated arguments of n-ary relations in text

Here we present the Xart system based on a three-step hybrid method using data mining approaches and syntactic analysis to automatically discover and...
Read more

New publication: Decision support system for eco-efficient biorefinery process comparison using a semantic approach.

Enzymatic hydrolysis of the main components of lignocellulosic biomass is one of the promising methods to further upgrading it into biofuels. Biomass...
Read more

Lilia Berrahou PhD defense took place the 29th of September 2015 at LIRMM Montpellier

The title of the PhD is N-ary relation arguments extraction from texts guided by a domain OTR.
Read more

@Web platform joint the Wheat Data Interoperability Initiative

@Web platform participates to the Wheat Data Interoperability Initiative. Our first contribution consists in proposing Biorefinery ontology for plant...
Read more

Aromatic component diffusion values capitalisation during AgroBio4 project (2015-2018)

Aromatic component diffusion values capitalisation will be done using @Web during AgroBio4 project (2015-2018).
Read more

A new methodological work about Ontology evolution accepted in MTSR'2015 conference

The paper "Ontology Evolution for Experimental Data in Food" accepted in MTSR'2015 conference.
Read more


@Web, a software to annotate heterogeneous scientific data sources guided by a termino-ontological resource

@Web is a semantic web application using a predefined vocabulary (called ontology in the following) organized as a taxonomy. @Web is a semi-automatic tool designed to help domain experts to annotate data found in scientific documents (publications, data sheets, ...). @Web project is a joint collaboration between UMR INRA MIA AgroParisTech/INRA, UMR INRA IATE, INRIA GraphiK, UMR CNRS Heudyasic, UMR INRA Mistea and Plastic platform (INRA CEPIA software platform).

We focus on data tables as they often contain a synthesis of experimental results published in scientific publications. The user downloads an HTML scientific document, then data tables are semi-automatically identified and extracted from the document. A graphical user-friendly interface helps the user to annotate data tables thanks to the ontology. Annotators may suggest evolutions of the ontology (new candidate terms of the vocabulary) which are managed by the ontology administrator. Metadata are associated with documents in order to assess documents’ reliability. Relevant annotated information from scientific data tables may be queried thank to a semantic browser using the ontology.