# The Return of Lexical Dependencies: Neural Lexicalized PCFGs

arXiv: https://arxiv.org/abs/2007.15135 · HTML: https://mlsanity.com/paper/2007.15135/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 19 of 19)

- [Grammar Prompting for Domain-Specific Language Generation with Large Language Models](https://mlsanity.com/paper/2305.19234/) (2023)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols](https://mlsanity.com/paper/2104.13727/) (2021)
- [Neural Bi-Lexicalized PCFG Induction](https://mlsanity.com/paper/2105.15021/) (2021)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs](https://mlsanity.com/paper/2205.00484/) (2022)
- [Hierarchical Phrase-based Sequence-to-Sequence Learning](https://mlsanity.com/paper/2211.07906/) (2022)
- [Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars](https://mlsanity.com/paper/2212.09140/) (2022)
- [Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers](https://mlsanity.com/paper/2306.00645/) (2023)
- [Co-training an Unsupervised Constituency Parser with Weak Supervision](https://mlsanity.com/paper/2110.02283/) (2021)
- [Dependency Induction Through the Lens of Visual Perception](https://mlsanity.com/paper/2109.09790/) (2021)
- [Scaling Structured Inference with Randomization](https://mlsanity.com/paper/2112.03638/) (2021)
- [Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences](https://mlsanity.com/paper/2303.08809/) (2023)
- [Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models](https://mlsanity.com/paper/2211.00479/) (2022)
- [Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?](https://mlsanity.com/paper/2206.14969/) (2022)
- [On the Compatibility of Generative AI and Generative Linguistics](https://mlsanity.com/paper/2411.10533/) (2024)
- [Understanding Syntactic Generalization in Structure-inducing Language Models](https://mlsanity.com/paper/2508.07969/) (2025)
- [Holographic Neural PCFG for Unsupervised Parsing](https://mlsanity.com/paper/2607.08063/) (2026)

## Abstract (arXiv)

In this paper we demonstrate that textitcontext free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies. This contrasts to the most popular current methods for grammar induction, which focus on discovering textiteither constituents textitor dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g. lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs which allow us to overcome sparsity problems and effectively induce both constituents and dependencies within a single model. Experiments demonstrate that this unified framework results in stronger results on both representations than achieved when modeling either formalism alone. Code is available at https://github.com/neulab/neural-lpcfg.