DE eng

Search in the Catalogues and Directories

Hits 1 – 8 of 8

1
Connectionist Learning to Read Aloud and Correlation to Human Data
In: http://www.let.rug.nl/~stoianov/ps/CS99_Reading_Stoianov_Stowe_Nerbonne.ps.gz (1999)
BASE
Show details
2
Connectionist learning to read aloud and correlation to human data
In: http://odur.let.rug.nl/~nerbonne/papers/cogsci99.pdf (1999)
BASE
Show details
3
Connectionist Grapheme to Phoneme Conversion: Exploring Distributed Representations
In: http://www-uilots.let.uu.nl/publications/clin1999/Pap/stoianov.ps (1999)
BASE
Show details
4
Connectionist Learning of Natural Language Lexical Phonotactics
In: http://www.let.rug.nl/~stoianov/ps/ml.conn.learn.nl.phonotactics.ps.gz (1998)
BASE
Show details
5
Exploring Phonotactics with Simple Recurrent Networks
In: http://www.let.rug.nl/~nerbonne/papers/clin98srn.ps (1998)
BASE
Show details
6
Modelling the phonotactic structure of natural language words with Simple Recurrent Networks
In: http://grid.let.rug.nl/~nerbonne/papers/clin97.Stoianov.Nerbonne.Bouma.PhonotacticsLearning.pdf (1998)
BASE
Show details
7
Modelling the phonotactic structure of natural language words with Simple Recurrent Networks
In: http://grid.let.rug.nl/~stoianov/ps/dutch.phonot.poster97.ps.gz (1997)
BASE
Show details
8
Modelling the phonotactic structure of natural language words with Simple Recurrent Networks
In: http://www.let.rug.nl/~stoianov/ps/clin97.Stoianov.Nerbonne.Bouma.PhonotacticsLearning.ps.gz (1997)
Abstract: Simple Recurrent Networks (SRN) are Neural Network (connectionist) models able to process natural language. Phonotactics concerns the order of symbols in words. We continued an earlier unsuccessful trial to model the phonotactics of Dutch word corpus with SRNs. In order to overcome the previously reported obstacles, a new method for network testing was developed - optimal threshold evaluation. This method is based on minimising the erroneous character prediction of a trained SRN. The network training was improved as well. The training words were presented to the network according to their frequencies, which emphasises the more frequent sequences. The achieved results are promising and provide a base for further study. 1. Introduction to connectionist natural language processing. It is still a challenge to process natural language with connectionist paradigms. Formal language theory provides more natural methods for exploring complex language phenomena, but if we search for an approach.
URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.9810
http://www.let.rug.nl/~stoianov/ps/clin97.Stoianov.Nerbonne.Bouma.PhonotacticsLearning.ps.gz
BASE
Hide details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
8
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern