Expectation Driven Learning of Phonology
نویسندگان
چکیده
Expectation Driven Learning of Phonology Gaja Jarosz Abstract This paper develops a novel approach to learning phonological hidden structure relying on underexplored expectation driven learning strategies rooted in the machine learning literature. A novel probabilistic grammatical representation that enables estimation of expectation driven learning updates, and two learning algorithms utilizing these updates, are introduced. The algorithms are shown to surpass the performance of existing error-driven learning models on a large test system with hidden metrical structure. The paper then shows that the learning strategies are fully general and can also be successfully applied to learning of an entirely different sort of hidden structure created by unknown underlying representations.
منابع مشابه
Noise robustness and stochastic tolerance of OT error-driven ranking algorithms
Recent counterexamples show that Harmonic Grammar (HG) error-driven learning (with the classical Perceptron reweighing rule) is not robust to noise and does not tolerate the stochastic implementation (Magri 2014, MS). This article guarantees that no analogous counterexamples are possible for proper Optimality Theory (OT) error-driven learners. In fact, a simple extension of the OT convergence a...
متن کاملConcordance-Based Data-Driven Learning Activities and Learning English Phrasal Verbs in EFL Classrooms
In spite of the highly beneficial applications of corpus linguistics in language pedagogy, it has not found its way into mainstream EFL. The major reasons seem to be the teachers’ lack of training and the unavailability of resources, especially computers in language classes. Phrasal verbs have been shown to be a problematic area of learning English as a foreign language due to their semantic op...
متن کاملLearnability and Markedness in Data-Driven Acquisition of Stress
This paper investigates the computational grounding of learning theories developed within a metrical phonology approach to stress assignment. In current research, the Principles and Parameters approach to learning stress is pervasive. We point out some inherent problems associated with this approach in learning the stress system of a particular language by setting parameters (the case of Dutch)...
متن کاملAlternating Projections for Learning with Expectation Constraints
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (Graca et al., 2008), maintains uncertainty during optimization unlike constra...
متن کامل