Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction

Jinwook Park, Kangil Kim

Abstract
Neural parameterization has significantly advanced unsupervised grammar induction. However, training these models with a traditional likelihood loss for all possible parses exacerbates two issues: 1) *structural optimization ambiguity* that arbitrarily selects one among structurally ambiguous optimal grammars despite the specific preference of gold parses, and 2) *structural simplicity bias* that leads a model to underutilize rules to compose parse trees. These challenges subject unsupervised neural grammar induction (UNGI) to inevitable prediction errors, high variance, and the necessity for extensive grammars to achieve accurate predictions. This paper tackles these issues, offering a comprehensive analysis of their origins. As a solution, we introduce *sentence-wise parse-focusing* to reduce the parse pool per sentence for loss evaluation, using the structural bias from pre-trained parsers on the same dataset.In unsupervised parsing benchmark tests, our method significantly improves performance while effectively reducing variance and bias toward overly simplistic parses. Our research promotes learning more compact, accurate, and consistent explicit grammars, facilitating better interpretability.
Anthology ID:
2024.findings-acl.898
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15124–15139
Language:
URL:
https://aclanthology.org/2024.findings-acl.898
DOI:
Bibkey:
Cite (ACL):
Jinwook Park and Kangil Kim. 2024. Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction. In Findings of the Association for Computational Linguistics ACL 2024, pages 15124–15139, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction (Park & Kim, Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.898.pdf
PDF Search