| ROA: | 353 |
|---|---|
| Title: | Learning Phonotactic Distributions |
| Authors: | Alan Prince, Bruce Tesar |
| Comment: | |
| Length: | 33 |
| Abstract: | Learning Phonotactic Distributions Alan Prince & Bruce Tesar Dept. of Linguistics and Center for Cognitive Science Rutgers University Many essentials of a language's phonology can be learned from distributional evidence, in the absence of detailed morphological analysis. But distributional learning from positive evidence encounters the subset problem in full force. Here we explore an approach in which the learning algorithm, based on the error- driven variant of Recursive Constraint Demotion (RCD: Tesar 1995, Tesar & Smolensky 1998), is persistently biased to place markedness constraints as high as possible, but aims to place faithfulness constraint as low as possible. The learner seeks only to reproduce the output from identical input, avoiding all concern with nontrivial underlying forms; under the M>>F bias this results in significant learning. (Hayes 1999 independently develops a similar approach from the same basic assumptions.) We introduce an explicit measure of the degree to which a hierarchy possesses M>>F structure, and we investigate the consequences of trying to maximize this measure by low placement of F in suitably biased versions of RCD. We argue that existing proposals by which M>>F structure is carried over from an initial state through a learning procedure blind to the M/F distinction, as in the different conceptions of Smolensky 1996 and Ito & Mester 1998, cannot accomplish this goal successfully, as they are currently understood. We conclude that Biased Constraint Demotion (BCD) must be used by the learner at each step. The key issue is deciding which F to rank when there is more than one F constraint to choose from. We suggest that the main desideratum is the 'freeing up' of further M constraints for ranking, though we also show that such decisions have further consequences downstream for the resultant hierarchy that may motivate a certain kind of 'look ahead' in the decision-making process. We also consider the issue of the ranking of special- general pairs of faithfulness constraints, arguing that the matter cannot be resolved by examining the structure of constraints in isolation. We show that special/general relations can be derived mid-hierarchy, on the one hand, and on the other, can arise between constraints that appear to be independent. We note that in sharp contrast to the faithfulness situation, special/general relations between markedness constraints are handled automatically by BCD; this provides learning-theoretic motivation for resolving the positional markedness vs. positional faithfulness controversy (Beckman 1998, Zoll 1998) and for deeper scrutiny of faithfulness theory as a whole. |
| Type: | Paper/tech report |
| Area/Keywords: | Learnability,Formal Analysis,Phonology,Psycholinguistics |
| Article: | Version 1 |