Unsupervised spectral learning of finite-state transducers

Finite-State Transducers (FST) are a standard tool for modeling paired inputoutput sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. presented a spectral algorithm for learning FST from samples of aligned input-o...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Bailly, Raphaël, Carreras Pérez, Xavier, Quattoni, Ariadna Julieta
Format:	Text Resource
Sprache:	eng
Schlagworte:	Finite State Transducers Spectral Learning Finite-state transducers Informàtica Intel·ligència artificial Llenguatge natural Transductors d'estats finits Àrees temàtiques de la UPC
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!