1 |
Recurrent Autoassociative Networks and Holistic Computations
|
|
|
|
In: http://odur.let.rug.nl/~stoianov/ps/ijcnn2000.Stoianov.RAN_Holistic_Computations.ps.gz (2000)
|
|
BASE
|
|
Show details
|
|
2 |
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
|
|
3 |
Connectionist learning to read aloud and correlation to human data
|
|
|
|
In: http://odur.let.rug.nl/~nerbonne/papers/cogsci99.pdf (1999)
|
|
BASE
|
|
Show details
|
|
4 |
Connectionist Grapheme to Phoneme Conversion: Exploring Distributed Representations
|
|
|
|
In: http://www-uilots.let.uu.nl/publications/clin1999/Pap/stoianov.ps (1999)
|
|
BASE
|
|
Show details
|
|
5 |
Recurrent Autoassociative Networks and Sequential Processing
|
|
|
|
In: http://www.let.rug.nl/~stoianov/ps/ijcnn99.Stoianov.ps.gz (1999)
|
|
BASE
|
|
Show details
|
|
6 |
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
|
|
7 |
Exploring Phonotactics with Simple Recurrent Networks
|
|
|
|
In: http://www.let.rug.nl/~nerbonne/papers/clin98srn.ps (1998)
|
|
BASE
|
|
Show details
|
|
8 |
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
|
|
9 |
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)
|
|
Abstract:
The very promising reported results of Neural Networks grammar modelling has motivated a lot of researchers to use them in linguistic analysis at each level of natural language - semantics, syntax, phonetics. The most popular connectionist model used for Natural Language Processing is the Simple Recurrent Network (SRN), invented by J. Elman and successfully used to model some grammars. However, some larger explorations in this area failed, such as some experiments with Dutch phonotactic modelling. The research project reported on here aimed at natural language phonotactics modelling. Some of the newly developed techniques for Neural Networks grammar modelling include a methodology for finding an optimal threshold and second, including the word frequency information during the training and evaluation process. They led to encouraging results, which allow us to claim that natural language words phonotactics can be learned by SRN's.
|
|
URL: http://grid.let.rug.nl/~stoianov/ps/dutch.phonot.poster97.ps.gz http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.440
|
|
BASE
|
|
Hide details
|
|
10 |
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)
|
|
BASE
|
|
Show details
|
|
|
|