Para acceder a los documentos con el texto completo, por favor, siga el siguiente enlace: http://hdl.handle.net/2117/96512
Título:
|
A Unified approach to natural language treatment
|
Autor/a:
|
Álvarez Canal, Jordi
|
Otros autores:
|
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
Abstract:
|
This paper proposes a learning-based methodology to deal with Natural Language. Our system tries to acquire a knowledge model from an analyzed text. After that, a new text can be analyzed by using that model. The methodology introduces a unified representation mechanism for every kind of information present in Natural Language treatment (corresponding to Natural Language phases in other systems). In this way, the acquired knowledge model can contain any kind of language information (lexical, syntactic, semantic, conceptual or even world-knowledge).
With this approach we are not trying to give an overall solution to
Natural Language treatment; but to solve Natural Language problems
using any kind of relevant information.
We also provide an inference mechanism that puts asside the idea of
Natural Language phase. |
Materia(s):
|
-Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial -Natural language |
Derechos:
|
|
Tipo de documento:
|
Artículo - Versión publicada Informe |
Compartir:
|
|
Mostrar el registro completo del ítem