Harmonic Grammar, Optimality Theory, and Syntax Learnability: An Empirical Exploration of Czech Word Order
This work addresses syntax learnability for linguists, but it is incremental as it builds on existing frameworks and algorithms.
The paper compared learning algorithms for Harmonic Grammar (HG) and Optimality Theory (OT) grammars, finding that HG's greater expressivity improved performance in predicting Czech word order, with the perceptron algorithm approaching an upper bound in accuracy on a test set.
This work presents a systematic theoretical and empirical comparison of the major algorithms that have been proposed for learning Harmonic and Optimality Theory grammars (HG and OT, respectively). By comparing learning algorithms, we are also able to compare the closely related OT and HG frameworks themselves. Experimental results show that the additional expressivity of the HG framework over OT affords performance gains in the task of predicting the surface word order of Czech sentences. We compare the perceptron with the classic Gradual Learning Algorithm (GLA), which learns OT grammars, as well as the popular Maximum Entropy model. In addition to showing that the perceptron is theoretically appealing, our work shows that the performance of the HG model it learns approaches that of the upper bound in prediction accuracy on a held out test set and that it is capable of accurately modeling observed variation.