Papers › Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
Jinwook Park, Kangil Kim
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Constituency Grammar Induction | PTB Diagnostic ECG Database | Parse-Focused (NT=4500) | Max F1 (WSJ) | 70.3 | #2 of 24 | Archive leaderboard | report |
| Constituency Grammar Induction | PTB Diagnostic ECG Database | Parse-Focused (NT=4500) | Mean F1 (WSJ) | 69.6 | #2 of 24 | Archive leaderboard | report |
| Constituency Grammar Induction | PTB Diagnostic ECG Database | Parse-Focused (NT=30) | Max F1 (WSJ) | 68.4 | #3 of 24 | Archive leaderboard | report |
| Constituency Grammar Induction | PTB Diagnostic ECG Database | Parse-Focused (NT=30) | Mean F1 (WSJ) | 67.4 | #3 of 24 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections