Título:
|
Structured prediction models via the matrix-tree theorem
|
Autor/a:
|
Koo, Terry; Globerson, Amir; Carreras Pérez, Xavier; Collins, Michael
|
Otros autores:
|
Universitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural |
Abstract:
|
This paper provides an algorithmic framework for learning statistical models involving directed spanning trees, or equivalently non-projective dependency structures. We show how partition functions and marginals for directed spanning trees can be computed by an adaptation of Kirchhoff’s Matrix-Tree Theorem. To demonstrate an application of the method, we perform experiments which use the algorithm in training both log-linear and max-margin dependency parsers. The new training methods give improvements in accuracy over perceptron-trained models. |
Abstract:
|
Peer Reviewed |
Materia(s):
|
-Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural -Computational linguistics -Lingüística computacional |
Derechos:
|
|
Tipo de documento:
|
Artículo - Versión presentada Objeto de conferencia |
Compartir:
|
|