Results 1 
4 of
4
Very efficient learning of structured classes of subsequential functions from positive data
"... In this paper, we present a new algorithm that can identify in polynomial time and data using positive examples any class of subsequential functions that share a particular finitestate structure. While this structure is given to the learner a priori, it allows for the exact learning of partial func ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
In this paper, we present a new algorithm that can identify in polynomial time and data using positive examples any class of subsequential functions that share a particular finitestate structure. While this structure is given to the learner a priori, it allows for the exact learning of partial functions, and both the time and data complexity of the algorithm are linear. We demonstrate the algorithm on examples from natural language phonology and morphology in which the needed structure has been argued to be plausibly known in advance. A procedure for making any subsequential transducer onward without changing its structure is also presented.
lif.univmrs.fr
"... We define two proper subclasses of subsequential functions based on the concept of Strict Locality (McNaughton and Papert, 1971; Rogers and Pullum, 2011; Rogers et al., 2013) for formal languages. They are called ..."
Abstract
 Add to MetaCart
(Show Context)
We define two proper subclasses of subsequential functions based on the concept of Strict Locality (McNaughton and Papert, 1971; Rogers and Pullum, 2011; Rogers et al., 2013) for formal languages. They are called
Learning Repairs for Marked Structures
"... Outputoriented theories of phonological grammar are in part motivated by ‘conspiracies ’ in which the same marked structure is targeted by a range of different processes. As an example, consider the ‘repair typology ’ that prevents a nasalvoiceless ..."
Abstract
 Add to MetaCart
Outputoriented theories of phonological grammar are in part motivated by ‘conspiracies ’ in which the same marked structure is targeted by a range of different processes. As an example, consider the ‘repair typology ’ that prevents a nasalvoiceless
Logic and the Generative Power of Autosegmental Phonology*
"... The current study examines the generative power of Autosegmental Phonology (Goldsmith, 1976, 1979, 1990) in the framework of Formal Language Theory, with which we can study the computational complexity of phonological phenomena and formalisms independent of specific theoretical frameworks in phonolo ..."
Abstract
 Add to MetaCart
(Show Context)
The current study examines the generative power of Autosegmental Phonology (Goldsmith, 1976, 1979, 1990) in the framework of Formal Language Theory, with which we can study the computational complexity of phonological phenomena and formalisms independent of specific theoretical frameworks in phonology. A methodology for a modeltheoretic study of autosegmental phonology with monadic secondorder logic