# Second-Order Unsupervised Neural Dependency Parsing

arXiv: https://arxiv.org/abs/2010.14720 · HTML: https://mlsanity.com/paper/2010.14720/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [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)
- [On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies](https://mlsanity.com/paper/2104.05694/) (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)
- [Linguistic Dependencies and Statistical Dependence](https://mlsanity.com/paper/2104.08685/) (2021)
- [Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs](https://mlsanity.com/paper/2205.00484/) (2022)
- [Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships](https://mlsanity.com/paper/2203.14260/) (2022)
- [Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars](https://mlsanity.com/paper/2212.09140/) (2022)
- [Understanding Syntactic Generalization in Structure-inducing Language Models](https://mlsanity.com/paper/2508.07969/) (2025)

## Abstract (arXiv)

Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose a novel design of the neural parameterization and optimization methods of the dependency models. In second-order models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set