Instance-Based Learning Algorithms
Machine Learning
A computational basis for phonology
Advances in neural information processing systems 2
Efficient learning of typical finite automata from random walks
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Class-based n-gram models of natural language
Computational Linguistics
Regular models of phonological rule systems
Computational Linguistics - Special issue on computational phonology
The acquisition of stress: a data-oriented approach
Computational Linguistics - Special issue on computational phonology
Computational optimality theory
Computational optimality theory
The String-to-String Correction Problem
Journal of the ACM (JACM)
Computational Phonology: A Constraint-Based Approach
Computational Phonology: A Constraint-Based Approach
Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning
Hidden Markov Model} Induction by Bayesian Model Merging
Advances in Neural Information Processing Systems 5, [NIPS Conference]
One-level phonology: autosegmental representations and rules as finite automata
Computational Linguistics
A discovery procedure for certain phonological rules
ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics
Phonological derivation in optimality theory
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Defense of the ansatz for dynamical hierarchies
Artificial Life
A new algorithm for the alignment of phonetic sequences
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Learning Local Transductions Is Hard
Journal of Logic, Language and Information
Measuring similarity between transliterations against noise data
ACM Transactions on Asian Language Information Processing (TALIP)
Speculative plan execution for information gathering
Artificial Intelligence
A Bayesian model of natural language phonology: generating alternations from underlying forms
SigMorPhon '08 Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology
Learning value predictors for the speculative execution of information gathering plans
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Maximum likelihood estimation of feature-based distributions
SIGMORPHON '10 Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology
Formal and empirical grammatical inference
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts of ACL 2011
Research on Language and Computation
Bounded copying is subsequential: implications for metathesis and reduplication
SIGMORPHON '12 Proceedings of the Twelfth Meeting of the Special Interest Group on Computational Morphology and Phonology
Hi-index | 0.02 |
A fundamental debate in the machine learning of language has been the role of prior knowledge in the learning process. Purely nativist approaches, such as the Principles and Parameters model, build parameterized linguistic generalizations directly into the learning system. Purely empirical approaches use a general, domain-independent learning rule (Error Back-Propagation, Instance-based Generalization, Minimum Description Length) to learn linguistic generalizations directly from the data.In this paper we suggest that an alternative to the purely nativist or purely empiricist learning paradigms is to represent the prior knowledge of language as a set of abstract learning biases, which guide an empirical inductive learning algorithm. We test our idea by examining the machine learning of simple Sound Pattern of English (SPE)-style phonological rules. We represent phonological rules as finite-state transducers that accept underlying forms as input and generate surface forms as output. We show that OSTIA, a general-purpose transducer induction algorithm, was incapable of learning simple phonological rules like flapping. We then augmented OSTIA with three kinds of learning biases that are specific to natural language phonology, and that are assumed explicitly or implicitly by every theory of phonology: faithfulness (underlying segments tend to be realized similarly on the surface), community (similar segments behave similarly), and context (phonological rules need access to variable in their context). These biases are so fundamental to generative phonology that they are left implicit in many theories. But explicitly modifying the OSTIA algorithm with these biases allowed it to learn more compact, accurate, and general transducers, and our implementation successfully learns a number of rules from English and German. Furthermore, we show that some of the remaining errors in our augmented model are due to implicit biases in the traditional SPE-style rewrite system that are not similarly represented in the transducer formalism, suggesting that while transducers may be formally equivalent to SPE-style rules, they may not have identical evaluation procedures.Because our biases were applied to the learning of very simple SPE-style rules, and to a non-psychologically-motivated and nonprobabilistic theory of purely deterministic transducers, we do not expect that our model as implemented has any practical use as a phonological learning device, nor is it intended as a cognitive model of human learning. Indeed, because of the noise and nondeterminism inherent to linguistic data, we feel strongly that stochastic algorithms for language induction are much more likely to be a fruitful research direction. Our model is rather intended to suggest the kind of biases that may be added to other empiricist induction models, and the way in which they may be added, in order to build a cognitively and computationally plausible learning model for phonological rules.