Open AccessA phonological encoding of Turkish for neural networks
Author(s) -
Kamil Stachowski
Publication year - 2015
Publication title -
homo politicus (academy of humanities and economics in lodz)
Language(s) - English
Resource type - Journals
eISSN - 2083-4624
pISSN - 1897-1059
DOI - 10.4467/20834624sl.12.023.0807
Subject(s) - turkish , encoding (memory) , suffix , artificial neural network , computer science , artificial intelligence , linguistics , natural language processing , speech recognition , arithmetic , mathematics , philosophy
The paper proposes a multi-dimensional, phonologically-aware numeric encoding of Turkish for use with neural networks. The system is evaluated and compared to PatPho (Li/MacWhinney 2002) in a test in which the network computes the shape of the past tense suffix
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom