Learning rule-based morpho-phonology
Ezer Rasin, Iddo Berger, Nur Lan, Roni Katzir
February 2018 

Speakers' knowledge of the sound pattern of their language -- their knowledge of morpho-phonology -- goes well beyond the plain phonetic forms of words. According to a long-standing model in linguistics, morpho-phonological knowledge is distributed between a lexicon with morphemes, usually referred to as Underlying Representations (URs), and context-sensitive rewrite rules that transform URs to surface forms. In this paper we provide what to our knowledge is the first unsupervised learner that acquires both URs and phonological rules, including both optionality and rule interaction (both transparent and opaque), from distributional cues alone. Our learner is based on the principle of Minimum Description Length (MDL) which -- like the closely related Bayesian approach -- aims at balancing the complexity of the grammar and its fit of the data.

Format:	[ pdf ]
Reference:	lingbuzz/003665 (please use that when you cite this article)
Published in:	Submitted
keywords:	learning, evaluation metrics, minimum description length, phonology, rule-based phonology, opacity, phonology
previous versions:	v1 [September 2017]
Downloaded:	1327 times

 

[ edit this article | back to article list ]