by Ivelin Stoianov, John Nerbonne
Computational Linguistics in the Netherlands
http://www.let.rug.nl/~nerbonne/papers/clin98srn.ps
Add To MetaCart
Abstract:
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 phonotactics. In addition, we conducted further analysis of neural network performance with regard to some variables such as word frequency, length, neighborhood density and error location. The results are compared with reported psycholinguistics analyses. This informal comparison 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.
Citations
|
1092
|
Finding Structure in Time
– Elman
- 1990
|
|
401
|
Parallel networks that learn to pronounce english text
– Sejnowski, Rosenberg
- 1987
|
|
226
|
A distributed, developmental model of word recognition and naming, Psychological Review 96(4
– Seidenberg, McClelland
- 1989
|
|
176
|
Understanding normal and impaired word reading: Computational principles in quasi-regular domains
– Plaut, McClelland, et al.
- 1996
|
|
38
|
Structure and function in the lexical system: Insights from distributed models of word reading and lexical decision
– Plaut
- 1997
|
|
36
|
Language acquisition and use: Learning and applying probabilistic constraints
– Seidenberg
- 1997
|
|
28
|
Structure and content in language production: A theory of frame constraints in phonological speech errors
– Dell, Juliano, et al.
- 1993
|
|
22
|
Bootstrapping word boundaries: A bottom-up corpus-based approach to speech segmentation, Cognitive
– Cairns, Shillcock, et al.
- 1997
|
|
16
|
Similarity neighborhoods of spoken words
– Luce, Pisoni, et al.
- 1990
|
|
15
|
The emergence of phonology from the interplay of speech comprehension and production: A distributed connectionist approach
– Plaut, Kello
- 1999
|
|
9
|
Syllable structure and the distribution of phonemes in English syllables
– Kessler, Treiman
- 1997
|
|
8
|
Learning distributed representations for syllables
– Gasser
- 1992
|
|
8
|
Modelling the phonotactic structure of natural language words with Simple Recurrent Networks
– Stoianov, Nerbonne, et al.
- 1998
|
|
6
|
Phonetic Distance between Dutch Dialects
– Nerbonne, Heeringa, et al.
- 1996
|
|
5
|
Recurrent neural-network learning of phonological regularities in turkish
– Rodd
- 1997
|
|
5
|
Recurrent Autoassociative Networks and Sequential Processing
– Stoianov
- 1999
|
|
4
|
The limitations of modeling finite state grammars with simple recurrent networks
– Sang, Erik
- 1995
|
|
3
|
Discovering phonotactic finite-state automata by genetic search
– Belz
- 1998
|
|
3
|
Statistical and connectionist modelling of the development of speech segmentation
– Shillcock, Cairns, et al.
- 1997
|
|
2
|
Tree-based analysis of simple recurrent network learning, 36 Annual Meeting of the Association for
– Stoianov
- 1998
|
|
1
|
D.Servan-Schreiber and J.L.McClelland(1989), Finite state automata and simple recurrent networks, Neural Computation
– Cleeremans
|
|
1
|
Segmentation of continuos speech using phonotactics
– McQueen
|
|
1
|
K.(1998), Machine Learning of Phonotactics
– Sang
|
