Papers › PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols

PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols

28 Apr 2021NAACL 2021 4arXiv:2104.13727archive 2025-07-28

Songlin Yang, Yanpeng Zhao, Kewei Tu

Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previous approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neural parameterization for the new form to improve unsupervised parsing performance. We evaluate our model across ten languages and empirically demonstrate the effectiveness of using more symbols. Our code: https://github.com/sustcsonglin/TN-PCFG

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sustcsonglin/TN-PCFG officialmentioned in paperpytorch report

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

Constituency Grammar InductionForm

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Grammar Induction PTB Diagnostic ECG Database TN-PCFG (p=500) Max F1 (WSJ) 61.4 #11 of 24 Archive leaderboard report
Constituency Grammar Induction PTB Diagnostic ECG Database TN-PCFG (p=500) Mean F1 (WSJ) 57.7 #11 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