La base de donnees Prolex pour le Taln: Noms propres geographiques

C.B. Irin, D. Maurel and O. Piton

Papiers d'Economie Mathématique et Applications from Université Panthéon-Sorbonne (Paris 1)

Abstract: In natural language processing, electronic dictionaries are used for lexical parsing. Its transform a raw text in a sequence of tagged words ; these tags are morphological and grammatical information. Unknown words make problem. Proper nouns are a part of them. The french Prolex project consists in creating a "tool box" with a relational electronic dictionary of proper nouns and systems of proper noun derivative identification (with the help of rules, local grammars, etc). We present here our data base of toponyms (place names), gentiles (inhabitant names) and derivated adjectives, with their links. Our dictionary is built from the relational database that we introduce here. We justify our choice of a database and we describe the associated environment ; then we deal about the specificity of foreign terms and we present the integration of the data of France and the data of the rest of the world.

Keywords: DICTIONNAIRES; LANGUES; TRADUCTION (search for similar items in EconPapers)
JEL-codes: Z00 Z10 (search for similar items in EconPapers)
Pages: 18 pages
Date: 1999
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:fth:pariem:1999.11

Access Statistics for this paper

More papers in Papiers d'Economie Mathématique et Applications from Université Panthéon-Sorbonne (Paris 1) France; Universite de Paris I - Pantheon- Sorbonne, 12 Place de Pantheon-75005 Paris, France. Contact information at EDIRC.
Bibliographic data for series maintained by Thomas Krichel ().