Title :
Distributed syntactic representations with an application to part-of-speech tagging
Author :
Schütze, Hinrich
Author_Institution :
Center for the Study of Language & Inf., Stanford Univ., CA, USA
Abstract :
The syntactic category of words is represented in a distributed manner by deriving part-of-speech representations from a text corpus by means of a large scale singular value decomposition. The representations are input to an artificial neural network, which is trained on two days of the New York Times News Service, attaining an accuracy of 92%-98% in tagging ambiguous lexical items
Keywords :
learning (artificial intelligence); neural nets; speech recognition; ambiguous lexical items; distributed syntactic representations; neural network; part-of-speech tagging; singular value decomposition; speech recognition; syntactic category; text corpus; Artificial neural networks; Large-scale systems; Matrix decomposition; Neural networks; Prototypes; Singular value decomposition; Sparse matrices; Tagging; Wire;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298779
