-
The ALVIS Format for Linguistically Annotated Documents
The paper describes the ALVIS annotation format designed for the indexing of large collections of documents in topic-specific search engines. This paper is exemplified... -
Using NLP to build the hypertextuel network of a back-of-the-book index
Relying on the idea that back-of-the-book indexes are traditional devices for navigation through large documents, we have developed a method to build a hypertextual... -
Building back-of-the-book indexes
24 pages -
Event-based Information Extraction for the biomedical domain: the Caderige pr...
This paper gives an overview of the Caderige project. This project involves teams from different areas (biology, machine learning, natural language processing) in... -
Primitives logiques et réseaux sémantiques : quel bilan pour la terminologie ?
. This paper aims at evaluating the contribution of semantic networks to the computational terminology. It focuses on the conceptual graph formalism and, at a lower... -
Quand la langue cause : paramètres d'une étude linguistique de la causalité
Starting from the fact causality and linguistics are strongly related, this paper tries to understand if the language can help to better understand the notion of... -
Une mesure de pertinence pour le tri de l'information dans un document
Nous nous intéressons à la construction des index de ``fin de livre'' qui sont des outils de navigation et de recherche d'information dans un document. Ce travail ets... -
Le réseau terminologique, un élément central pour la construction d'index de ...
Cet article montre comment les outils de structuration de terminologie qui établissent des liens sémantiques entre termes (hyperonymie, synonymie...) contribuent à la... -
Semi-automatic method for the construction of a document index
This paper deals with document indexes, which somteimes appear at the back of books and list their main subjects. It shows how recent advances in natural language... -
Ontologies and Information Extraction
LIPN Internal Report -
Histoire et avenir des index de fin de livre
This dataset has no description
-
Un modèle pour unifier la gestion de ressources linguistiques en contexte mul...
The proper functioning of Intuition, Sinequa's platform for information retrieval, depends on the development and integration of a large number of linguistic...
