Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction

TL;DR

This paper demonstrates that depth-bounding significantly improves the accuracy of unsupervised PCFG induction by effectively limiting search space, with evaluations showing competitive results across multiple languages.

Contribution

It introduces a chart-based Bayesian PCFG inducer with switchable depth bounds, providing a direct comparison of bounded versus unbounded induction within the same system.

Findings

Depth-bounding increases induction accuracy.

Bounded models outperform unbounded models in experiments.

Effective across English, Chinese, and German.

Abstract

There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016; Jin et al., 2018). Modern depth-bounded grammar inducers have been shown to be more accurate than early unbounded PCFG inducers, but this technique has never been compared against unbounded induction within the same system, in part because most previous depth-bounding models are built around sequence models, the complexity of which grows exponentially with the maximum allowed depth. The present work instead applies depth bounds within a chart-based Bayesian PCFG inducer (Johnson et al., 2007b), where bounding can be switched on and off, and then samples trees with and without bounding. Results show that depth-bounding is indeed significantly effective in limiting the search space of the inducer and thereby increasing the accuracy of the resulting parsing model. Moreover, parsing results on English, Chinese and German show that this bounded model with a new inference technique is able to produce parse trees more accurately than or competitively with state-of-the-art constituency-based grammar induction models.