VENSES, a linguistically-based system for semantic evaluation

Empreu sempre aquest identificador per citar o enllaçar aquest ítem http://hdl.handle.net/10045/1350
Información del item - Informació de l'item - Item information
Títol: VENSES, a linguistically-based system for semantic evaluation
Autors: Delmonte, Rodolfo
Paraules clau: Parsing | Dependency structures | Logical forms | Semantic evaluation
Data de publicació: de setembre-2005
Editor: Sociedad Española para el Procesamiento del Lenguaje Natural
Citació bibliogràfica: DELMONTE, Rodolfo. “VENSES, a linguistically-based system for semantic evaluation”. Procesamiento del lenguaje natural. Nº 35 (sept. 2005), pp. 449-450
Resum: The system for semantic evaluation VENSES (Venice Semantic Evaluation System) is organized as a pipeline of two subsystems: the first is a reduced version of GETARUN, our system for Text Understanding. The output of the system is a flat list of head-dependent structures (HDS) with Grammatical Relations (GRs) and Semantic Roles (SRs) labels. The evaluation system is made up of two main modules: the first is a sequence of linguistic rule-based subcalls; the second is a quantitatively based measurement of input structures. VENSES measures semantic similarity which may range from identical linguistic items, to synonymous or just morphologically derivable. Both modules go through General Consistency checks which are targeted to high level semantic attributes like presence of modality, negation, and opacity operators, temporal and spatial location checks. Results in cws, accuracy and precision are homogeneous for both training and test corpus and fare higher than 60%.
URI: http://hdl.handle.net/10045/1350
ISSN: 1135-5948
Idioma: eng
Tipus: info:eu-repo/semantics/article
Apareix a la col·lecció: Procesamiento del Lenguaje Natural - Nº 35 (septiembre 2005)

Arxius per aquest ítem:
Arxius per aquest ítem:
Arxiu Descripció Tamany Format  
ThumbnailPLN_35_59.pdf72,44 kBAdobe PDFObrir Vista prèvia


Tots els documents dipositats a RUA estan protegits per drets d'autors. Alguns drets reservats.