# Grammatical information in BERT sentence embeddings as two-dimensional arrays

arXiv: https://arxiv.org/abs/2312.09890 · HTML: https://mlsanity.com/paper/2312.09890/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [ChatGPT: The End of Online Exam Integrity?](https://mlsanity.com/paper/2212.09292/) (2022)
- [Probing for the Usage of Grammatical Number](https://mlsanity.com/paper/2204.08831/) (2022)
- [Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans](https://mlsanity.com/paper/2006.11098/) (2020)
- [Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks](https://mlsanity.com/paper/1802.09091/) (2018)
- [Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization](https://mlsanity.com/paper/2011.02417/) (2020)
- [Distinct patterns of syntactic agreement errors in recurrent networks and humans](https://mlsanity.com/paper/1807.06882/) (2018)
- [Representation biases in sentence transformers](https://mlsanity.com/paper/2301.13039/) (2023)
- [Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks](https://mlsanity.com/paper/2205.10866/) (2022)

## Built on by (most cited first, 4 of 4)

- [Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification](https://mlsanity.com/paper/2407.18119/) (2024)
- [Exploring syntactic information in sentence embeddings through multilingual subject-verb agreement](https://mlsanity.com/paper/2409.06567/) (2024)
- [Exploring Italian sentence embeddings properties through multi-tasking](https://mlsanity.com/paper/2409.06622/) (2024)
- [RAGe: A Retrieval-Augmented Generation Evaluation Framework](https://mlsanity.com/paper/2605.27445/) (2026)

## Abstract (arXiv)

Sentence embeddings induced with various transformer architectures encode much semantic and syntactic information in a distributed manner in a one-dimensional array. We investigate whether specific grammatical information can be accessed in these distributed representations. Using data from a task developed to test rule-like generalizations, our experiments on detecting subject-verb agreement yield several promising results. First, we show that while the usual sentence representations encoded as one-dimensional arrays do not easily support extraction of rule-like regularities, a two-dimensional reshaping of these vectors allows various learning architectures to access such information. Next, we show that various architectures can detect patterns in these two-dimensional reshaped sentence embeddings and successfully learn a model based on smaller amounts of simpler training data, which performs well on more complex test data. This indicates that current sentence embeddings contain information that is regularly distributed, and which can be captured when the embeddings are reshaped into higher dimensional arrays. Our results cast light on representations produced by language models and help move towards developing few-shot learning approaches.