The String-to-String Correction Problem
Journal of the ACM (JACM)
Automatic rule induction for unknown-word guessing
Computational Linguistics
A simple rule-based part of speech tagger
ANLC '92 Proceedings of the third conference on Applied natural language processing
Terminological variation, a means of identifying research topics from texts
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Surface grammatical analysis for the extraction of terminological noun phrases
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 3
Syntagmatic and paradigmatic representations of term variation
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Joint knowledge capture for grammars and ontologies
Proceedings of the 1st international conference on Knowledge capture
An integrated, dual learner for grammars and ontologies
Data & Knowledge Engineering
Compilation of specialized comparable corpora in French and Japanese
BUCC '09 Proceedings of the 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora
Automatic acquisition of a slovak lexicon from a raw corpus
TSD'05 Proceedings of the 8th international conference on Text, Speech and Dialogue
Ontologies and terminologies: Continuum or dichotomy?
Applied Ontology - Ontologies and Terminologies: Continuum or Dichotomy?
Hi-index | 0.00 |
We present the identification in corpora of French relational adjectives (RAdj) such as gazeux (gascous) which is derived from the noun gaz (gas). RAdj appearing in nominal phrases are interesting for terminology acquisition because they hold a naming function. The derivational rules employed to compute the noun from which has been derived the RAdj are acquired semi-automatically from a tagged and a lemmatized corpora. These rules are then integrated into a termer which identifies RAdj thanks to their property of being paraphrasable by a prepositional phrase. RAdj and compound nouns which include a RAdj are then quantified, their linguistic precision is measured and their informative status is evaluated thanks to a thesaurus of the domain.