# On the Role of Supervision in Unsupervised Constituency Parsing

arXiv: https://arxiv.org/abs/2010.02423 · HTML: https://mlsanity.com/paper/2010.02423/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [Substructure Substitution: Structured Data Augmentation for NLP](https://mlsanity.com/paper/2101.00411/) (2021)
- [PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols](https://mlsanity.com/paper/2104.13727/) (2021)
- [TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding](https://mlsanity.com/paper/2205.06153/) (2022)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars](https://mlsanity.com/paper/2212.09140/) (2022)
- [Co-training an Unsupervised Constituency Parser with Weak Supervision](https://mlsanity.com/paper/2110.02283/) (2021)
- [Learning a Grammar Inducer from Massive Uncurated Instructional Videos](https://mlsanity.com/paper/2210.12309/) (2022)
- [The Emergence of Chunking Structures with Hierarchical RNN](https://mlsanity.com/paper/2309.04919/) (2023)
- [Audio-Visual Neural Syntax Acquisition](https://mlsanity.com/paper/2310.07654/) (2023)
- [TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping](https://mlsanity.com/paper/2311.02355/) (2023)
- [Learning Language Structures through Grounding](https://mlsanity.com/paper/2406.09662/) (2024)
- [Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models](https://mlsanity.com/paper/2211.00479/) (2022)
- [Data Augmentation for Machine Translation via Dependency Subtree Swapping](https://mlsanity.com/paper/2307.07025/) (2023)
- [Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing](https://mlsanity.com/paper/2402.13433/) (2024)
- [Unsupervised and Few-shot Parsing from Pretrained Language Models](https://mlsanity.com/paper/2206.04980/) (2022)
- [Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?](https://mlsanity.com/paper/2206.14969/) (2022)
- [Student as an Inherent Denoiser of Noisy Teacher](https://mlsanity.com/paper/2312.10185/) (2023)
- [Grammar Induction from Visual, Speech and Text](https://mlsanity.com/paper/2410.03739/) (2024)

## Abstract (arXiv)

We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.