PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
This work addresses a computational bottleneck for researchers in NLP, allowing more scalable unsupervised parsing, though it is incremental as it builds on existing neural PCFG methods.
The paper tackles the scalability issue of neural PCFGs in unsupervised grammar induction by introducing a tensor decomposition-based parameterization that reduces computational complexity from cubic to quadratic, enabling the use of many more symbols and improving parsing performance across ten languages.
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