Using decision trees to learn lexical information in a linguistics-based NLP system

Marisa Jiménez, Martine Pettenaro


Abstract
This paper describes the use of decision trees to learn lexical information for the enrichment of our natural language processing (NLP) system. Our approach to lexical learning differs from other approaches in the field in that our machine learning techniques exploit a deep knowledge understanding system. After the introduction we present the overall architecture of our lexical learning module. In the following sections we present a showcase of lexical learning using decision trees: we learn verbs that take a human subject in Spanish and French.
Anthology ID:
2003.jeptalnrecital-poster.13
Volume:
Actes de la 10ème conférence sur le Traitement Automatique des Langues Naturelles. Posters
Month:
June
Year:
2003
Address:
Batz-sur-Mer, France
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
373–378
Language:
URL:
https://aclanthology.org/2003.jeptalnrecital-poster.13
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2003.jeptalnrecital-poster.13.pdf