Search papers, labs, and topics across Lattice.
This paper introduces the Holographic Neural PCFG (Hol-PCFG), which reformulates the scoring of grammar rules in probabilistic context-free grammars (PCFGs) by leveraging algebraic relations among grammar-symbol embeddings. By employing Holographic Embeddings to model left-child, right-child, and lexical-emission relations, Hol-PCFG provides interpretable rule probabilities while significantly reducing the number of parameters required for rule scoring. The model achieves state-of-the-art performance in unsupervised parsing across six languages, including the ability to parse Japanese directly from characters, while also enhancing training stability and efficiency.
Achieving state-of-the-art parsing performance with 99.94% fewer rule-scoring parameters, Hol-PCFG transforms how we interpret grammar rules in unsupervised parsing.
Unsupervised constituency parsing aims to accurately induce latent tree structures from raw text alone. Recent neural parameterizations of PCFGs achieve strong performance in both supervised and unsupervised parsing, yet rely on high-capacity black-box networks for rule scoring -- as exemplified by the Neural PCFG family -- leaving rule probabilities without an interpretable mathematical form. In this paper, we propose Holographic Neural PCFG (Hol-PCFG), which recasts PCFG rule scoring as algebraic relation modeling among grammar-symbol embeddings. Hol-PCFG adapts Holographic Embeddings (Nickel et al., 2016), which scores knowledge-graph triples via circular correlation, to the left-child, right-child, and lexical-emission relations over torus-constrained embeddings, giving every rule probability a closed form that carries the intrinsic structure of grammar rules by construction. Hol-PCFG achieves state-of-the-art parsing performance in six languages while cutting rule-scoring parameters by 99.94% relative to the baseline model and training more stably. Additionally, we demonstrate that Hol-PCFG can parse Japanese directly from characters without any morphological segmentation, retaining nearly the same morpheme-level performance.
