# Self-Training for Unsupervised Parsing with PRPN

arXiv: https://arxiv.org/abs/2005.13455 · HTML: https://mlsanity.com/paper/2005.13455/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 3 of 3)

- [Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation](https://mlsanity.com/paper/2311.08640/) (2023)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [Co-training an Unsupervised Constituency Parser with Weak Supervision](https://mlsanity.com/paper/2110.02283/) (2021)

## Abstract (arXiv)

Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage aggregated annotations predicted by copies of our model as supervision for future copies. To be able to use our model's predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a) such that it can be trained in a semi-supervised fashion. We then add examples with parses predicted by our model to our unlabeled UP training data. Our self-trained model outperforms the PRPN by 8.1% F1 and the previous state of the art by 1.6% F1. In addition, we show that our architecture can also be helpful for semi-supervised parsing in ultra-low-resource settings.