Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction
This addresses a critical bottleneck in unsupervised grammar induction for language processing, enabling more efficient and interpretable models.
The paper tackled the problem of probability distribution collapse in unsupervised neural grammar induction, which causes unnecessarily large and underperforming grammars, and introduced a targeted solution that substantially improves parsing performance and enables more compact grammars across multiple languages.
Unsupervised neural grammar induction aims to learn interpretable hierarchical structures from language data. However, existing models face an expressiveness bottleneck, often resulting in unnecessarily large yet underperforming grammars. We identify a core issue, $\textit{probability distribution collapse}$, as the underlying cause of this limitation. We analyze when and how the collapse emerges across key components of neural parameterization and introduce a targeted solution, $\textit{collapse-relaxing neural parameterization}$, to mitigate it. Our approach substantially improves parsing performance while enabling the use of significantly more compact grammars across a wide range of languages, as demonstrated through extensive empirical analysis.