# Probing for Constituency Structure in Neural Language Models

arXiv: https://arxiv.org/abs/2204.06201 · HTML: https://mlsanity.com/paper/2204.06201/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models](https://mlsanity.com/paper/1812.09355/) (2018)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Analyzing Individual Neurons in Pre-trained Language Models](https://mlsanity.com/paper/2010.02695/) (2020)
- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [Conditional probing: measuring usable information beyond a baseline](https://mlsanity.com/paper/2109.09234/) (2021)
- [Probing BERT in Hyperbolic Spaces](https://mlsanity.com/paper/2104.03869/) (2021)
- [Refining Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/2104.09635/) (2021)
- [A Tale of a Probe and a Parser](https://mlsanity.com/paper/2005.01641/) (2020)
- [Deep RNNs Encode Soft Hierarchical Syntax](https://mlsanity.com/paper/1805.04218/) (2018)
- [On the Linguistic Representational Power of Neural Machine Translation Models](https://mlsanity.com/paper/1911.00317/) (2019)
- [NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks](https://mlsanity.com/paper/1812.09359/) (2018)
- [Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing](https://mlsanity.com/paper/2106.02559/) (2021)
- [Parsing as Pretraining](https://mlsanity.com/paper/2002.01685/) (2020)

## Built on by (most cited first, 14 of 14)

- [Physics of Language Models: Part 1, Learning Hierarchical Language Structures](https://mlsanity.com/paper/2305.13673/) (2023)
- [Do Transformers Parse while Predicting the Masked Word?](https://mlsanity.com/paper/2303.08117/) (2023)
- [Evaluating Neuron Interpretation Methods of NLP Models](https://mlsanity.com/paper/2301.12608/) (2023)
- [Morphosyntactic probing of multilingual BERT models](https://mlsanity.com/paper/2306.06205/) (2023)
- [Context-Free Recognition with Transformers](https://mlsanity.com/paper/2601.01754/) (2026)
- [Probing with Noise: Unpicking the Warp and Weft of Embeddings](https://mlsanity.com/paper/2210.12206/) (2022)
- [Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representations](https://mlsanity.com/paper/2402.11608/) (2024)
- [Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?](https://mlsanity.com/paper/2403.02009/) (2024)
- [The Compositional Architecture of Regret in Large Language Models](https://mlsanity.com/paper/2506.15617/) (2025)
- [Reconstruction Probing](https://mlsanity.com/paper/2212.10792/) (2022)
- [Geospatial Mechanistic Interpretability of Large Language Models](https://mlsanity.com/paper/2505.03368/) (2025)
- [Cross-Layer Discrete Concept Discovery for Interpreting Language Models](https://mlsanity.com/paper/2506.20040/) (2025)
- [What Makes Two Language Models Think Alike?](https://mlsanity.com/paper/2406.12620/) (2024)
- [Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork](https://mlsanity.com/paper/2610.16547/) (2026)

## Abstract (arXiv)

In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing techniques based on diagnostic classifiers, we assess the accuracy of representing constituents of different categories within the neuron activations of a LM such as RoBERTa. In order to make sure that our probe focuses on syntactic knowledge and not on implicit semantic generalizations, we also experiment on a PTB version that is obtained by randomly replacing constituents with each other while keeping syntactic structure, i.e., a semantically ill-formed but syntactically well-formed version of the PTB. We find that 4 pretrained transfomer LMs obtain high performance on our probing tasks even on manipulated data, suggesting that semantic and syntactic knowledge in their representations can be separated and that constituency information is in fact learned by the LM. Moreover, we show that a complete constituency tree can be linearly separated from LM representations.