Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Extraction de termes, reconnaissance et labellisation de relations dans un thésaurus (1002.0215v1)

Published 1 Feb 2010 in cs.IR

Abstract: Within the documentary system domain, the integration of thesauri for indexing and retrieval information steps is usual. In libraries, documents own rich descriptive information made by librarians, under descriptive notice based on Rameau thesaurus. We exploit two kinds of information in order to create a first semantic structure. A step of conceptualization allows us to define the various modules used to automatically build the semantic structure of the indexation work. Our current work focuses on an approach that aims to define an ontology based on a thesaurus. We hope to integrate new knowledge characterizing the territory of our structure (adding "toponyms" and links between concepts) thanks to a geographic information system (GIS).

Citations (2)

Summary

We haven't generated a summary for this paper yet.