Published September 1996 | Version v1
Journal article

Phonematic translation of Polish texts by the neural network

  • 1. Institute of Computer Science, Jagiellonian University, Cracow (Poland)
  • 2. Institute of Polish Philology, Jagiellonian University, Cracow (Poland)

Description

Using the back propagation algorithm, we have trained the feed forward neural network to pronounce Polish language, more precisely to translate Polish text into its phonematic counterpart. Depending on the input coding and network architecture, 88%-95% translation efficiency was achieved. (author)

Additional details

Publishing Information

Journal Title
Acta Physica Polonica. Series B
Journal Volume
27
Journal Issue
9
Journal Page Range
p. 2253-2264
ISSN
0587-4254

INIS

Country of Publication
Poland
Country of Input or Organization
Poland
INIS RN
29037718
Subject category
S99: GENERAL AND MISCELLANEOUS;
Descriptors DEI
COMPUTER CODES; COMPUTER NETWORKS; MACHINE TRANSLATIONS; MATHEMATICAL MODELS; NEURAL NETWORKS; TRANSLATORS
Descriptors DEC
COMPUTER CODES

Optional Information

Contract/Grant/Project number
KBN Grants No. PB2 P03B 196 09 and PB2 P302 252 06
Notes
16 refs, 1 fig., 5 tabs
Funding organization
Polish State Committee for Scientific Research, Warsaw (Poland)