Stoianov, Ivo, John Nerbonne & Huub Bouma [1997], Modelling the phonotactic structure of natural language words with Simple Recurrent Networks, in `CLIN '97'. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
An FGREP Investigation into Phonotactics - Kleiweg, Nerbonne (1999) (2 citations) Self-citation (Nerbonne) (Correct)
....processing, but chose Dutch monosyllables as domain. Although he improved on Cleeremans setup in several respects, his SRNs failed to learn Dutch phonotactics, and Tjong Kim Sang concluded that neural learning paradigms were not yet sophisticated enough to compete with others in this domain. Stoianov, Nerbonne Bouma [1997] reported better performance, however. We apply a neural network to phonotactic processing in the same way as Tjong Kim Sang [1998] and Stoianov et al. 1997] did. The network is presented with (monosyllabic) words, one letter at a time, and the network has to learn to predict the next letter. ....
....Tjong Kim Sang concluded that neural learning paradigms were not yet sophisticated enough to compete with others in this domain. Stoianov, Nerbonne Bouma [1997] reported better performance, however. We apply a neural network to phonotactic processing in the same way as Tjong Kim Sang [1998] and Stoianov et al. 1997] did. The network is presented with (monosyllabic) words, one letter at a time, and the network has to learn to predict the next letter. When training is completed, the network is tested, measuring how well it performs its task processing true words, compared to processing random strings. Tjong ....
[Article contains additional citation context not shown here]
Stoianov, Ivo, John Nerbonne & Huub Bouma [1997], Modelling the phonotactic structure of natural language words with Simple Recurrent Networks, in `CLIN '97'.
Recurrent Autoassociative Networks: Developing Distributed.. - Stoianov Self-citation (Stoianov) (Correct)
No context found.
Stoianov, I. P., Nerbonne, J., and Bouma, H., Modelling the phonotactic structure of natural language words with simple recurrent networks, in Computational Linguistics in the Netherlands, Coppen, P.-A., van Halteren, H., and Teunissen, L., Eds., Rodopi, Amsterdam, 77, 1997.
Exploring Phonotactics with Simple Recurrent Networks - Stoianov, Nerbonne (1998) (1 citation) Self-citation (Stoianov Nerbonne) (Correct)
.... Phonotactics with Simple Recurrent Networks Ivelin Stoianov and John Nerbonne University of Groningen, Faculty of Arts, Email: fstoianov, nerbonneg let.rug.nl Abstract Stoianov, Nerbonne and Bouma (1998) trained Simple Recurrent Networks (SRNs) on graphotactics of Dutch monosyllabic words, overcoming shortcomings of previous implementations. The current report is a continuation of our earlier research, but using phonetic data representations instead of orthographic, that is, learning ....
....of SRNs and human performance suggests that SRNs can be used for modeling natural language processing. 1 Introduction studying lexical constraints with SRNs. The present paper reports on a project investigating how well natural language phonotactics may be learned using neural networks (NN) (Stoianov, Nerbonne, and Bouma 1998, hereafter SNB98) which is interesting from different perspectives. Firstly, it challenges connectionism to tackle symbolic problems Tjong Kim Sang (1995; 1998) reported that symbolic and stochastic methods performed well on this problem, but connectionist techniques were not that successful. ....
[Article contains additional citation context not shown here]
Stoianov, I. P., Nerbonne, J. and Bouma, H.(1998), Modelling the phonotactic structure of natural language words with simple recurrent networks, in v. H.
An FGREP Investigation into Phonotactics - Kleiweg, Nerbonne (1999) (2 citations) Self-citation (Nerbonne) (Correct)
....processing, but chose Dutch monosyllables as domain. Although he improved on Cleeremans setup in several respects, his SRNs failed to learn Dutch phonotactics, and Tjong Kim Sang concluded that neural learning paradigms were not yet sophisticated enough to compete with others in this domain. Stoianov, Nerbonne and Bouma (1997) reported better performance, however. We apply a neural network to phonotactic processing in the same way as Tjong Kim Sang (1998) and Stoianov et al. 1997) did. The network is presented with (monosyllabic) words, one letter at a time, and the network has to learn to predict the next letter. ....
....Kim Sang concluded that neural learning paradigms were not yet sophisticated enough to compete with others in this domain. Stoianov, Nerbonne and Bouma (1997) reported better performance, however. We apply a neural network to phonotactic processing in the same way as Tjong Kim Sang (1998) and Stoianov et al. 1997) did. The network is presented with (monosyllabic) words, one letter at a time, and the network has to learn to predict the next letter. When training is completed, the network is tested, measuring how well it performs its task processing true words, compared to processing random strings. Tjong ....
[Article contains additional citation context not shown here]
Stoianov, I., Nerbonne, J. and Bouma, H.(1997), Modelling the phonotactic structure of natural language words with Simple Recurrent Networks, CLIN '97.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC