Paper: Predicting Romanian Stress Assignment

ACL ID E14-4013
Title Predicting Romanian Stress Assignment
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014

We train and evaluate two models for Ro- manian stress prediction: a baseline model which employs the consonant-vowel struc- ture of the words and a cascaded model with averaged perceptron training con- sisting of two sequential models ? one for predicting syllable boundaries and another one for predicting stress placement. We show in this paper that Romanian stress is predictable, though not deterministic, by using data-driven machine learning tech- niques.