A Computational Theory of Writing Systems (Studies in Natural Language Processing)
A Computational Theory of Writing Systems (Studies in Natural Language Processing)
Unsupervised multilingual learning
Unsupervised multilingual learning
Universal grapheme-to-phoneme prediction over Latin alphabets
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Hi-index | 0.00 |
We describe work in progress on using quantitative methods to classify writing systems according to Sproat's (2000) classification grid using unannotated data. We specifically propose two quantitative tests for determining the type of phonography in a writing system, and its degree of logography, respectively.