Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Park, Jinwook, Kim, Kangil
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.20734
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914055906656256
author Park, Jinwook
Kim, Kangil
author_facet Park, Jinwook
Kim, Kangil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction
Park, Jinwook
Kim, Kangil
Computation and Language
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.
title Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction
topic Computation and Language
url https://arxiv.org/abs/2509.20734