En este artículo se analizan varios tipos de gramáticas independientes del contexto probabilísticas obtenidas a partir de corpus etiquetados sintácticamente (treebanks). Estas gramáticas se utilizan para la desambiguación léxica y sintáctica de frases procedentes del lenguaje natural. Los modelos que aquí se estudian son los siguientes: (1) uno que simplemente extrae las reglas contenidas en el corpus y cuenta el número de ocurrencias de cada una; (2) un modelo que además almacena información acerca de la categoría sintáctica del nodo padre, y (3) un modelo que extrae y estima las probabilidades de las reglas almacenando información acerca de la categoría sintáctica de los hijos. Este último permite análisis sintácticos más eficientes, dism...
Presentamos una técnica heurística para convertir un corpus anotado sintácticamente dentro del form...
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Gramm...
Statistical NL G has largely meant n-gram modelling which has the considerable advantages of lending...
In this paper, we compare three different approaches to build a probabilistic context-free grammar f...
Probabilistic k-testable models (usually known as k-gram models in the case of strings) can be easil...
National audienceThis work presents a method and a tool for automatic extraction and exploration of ...
Probabilistic k-testable models (usually known as k-gram models in the case of strings) can be easil...
En este artículo presentamos el desarrollo de un nuevo recurso de código abierto para el español: el...
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage g...
Tool to explore treebanks.Extract a context-free grammar (CFG) and properties over the CFG rules.Gen...
En este artículo estudiamos el problema de la estimación de gramáticas incontextuales estocásticas ...
Institute for Communicating and Collaborative SystemsThis dissertation is concerned with the creatio...
The thesis focuses on learning syntactic tree structures by generalizing over an- notated treebanks....
By a \tree-bank grammar " we mean a context-free grammar cre-ated by reading the production rul...
This paper examines the usefulness of corpus-derived probabilistic grammars as a basis for the auto-...
Presentamos una técnica heurística para convertir un corpus anotado sintácticamente dentro del form...
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Gramm...
Statistical NL G has largely meant n-gram modelling which has the considerable advantages of lending...
In this paper, we compare three different approaches to build a probabilistic context-free grammar f...
Probabilistic k-testable models (usually known as k-gram models in the case of strings) can be easil...
National audienceThis work presents a method and a tool for automatic extraction and exploration of ...
Probabilistic k-testable models (usually known as k-gram models in the case of strings) can be easil...
En este artículo presentamos el desarrollo de un nuevo recurso de código abierto para el español: el...
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage g...
Tool to explore treebanks.Extract a context-free grammar (CFG) and properties over the CFG rules.Gen...
En este artículo estudiamos el problema de la estimación de gramáticas incontextuales estocásticas ...
Institute for Communicating and Collaborative SystemsThis dissertation is concerned with the creatio...
The thesis focuses on learning syntactic tree structures by generalizing over an- notated treebanks....
By a \tree-bank grammar " we mean a context-free grammar cre-ated by reading the production rul...
This paper examines the usefulness of corpus-derived probabilistic grammars as a basis for the auto-...
Presentamos una técnica heurística para convertir un corpus anotado sintácticamente dentro del form...
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Gramm...
Statistical NL G has largely meant n-gram modelling which has the considerable advantages of lending...