# Harmonic Grammar, Optimality Theory, and Syntax Learnability: An Empirical Exploration of Czech Word Order

## TL;DR

This paper empirically compares Harmonic Grammar and Optimality Theory learning algorithms, demonstrating that HG's greater expressivity leads to better Czech word order prediction, with the perceptron performing notably well.

## Contribution

It provides a systematic comparison of HG and OT learning algorithms and shows HG's advantages in modeling Czech word order and variation.

## Key findings

- HG outperforms OT in Czech word order prediction
- Perceptron learns HG models approaching upper bound accuracy
- HG models effectively capture observed variation

## Abstract

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.