# Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

arXiv: https://arxiv.org/abs/2402.06492 · HTML: https://mlsanity.com/paper/2402.06492/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 84 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [On the Practical Computational Power of Finite Precision RNNs for Language Recognition](https://mlsanity.com/paper/1805.04908/) (2018)
- [The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers](https://mlsanity.com/paper/2108.12284/) (2021)
- [Compositional generalization through meta sequence-to-sequence learning](https://mlsanity.com/paper/1906.05381/) (2019)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [Linguistically-Informed Self-Attention for Semantic Role Labeling](https://mlsanity.com/paper/1804.08199/) (2018)
- [Learning to Recombine and Resample Data for Compositional Generalization](https://mlsanity.com/paper/2010.03706/) (2020)
- [Meta-Learning to Compositionally Generalize](https://mlsanity.com/paper/2106.04252/) (2021)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks](https://mlsanity.com/paper/1807.07545/) (2018)
- [Compositional Generalization for Primitive Substitutions](https://mlsanity.com/paper/1910.02612/) (2019)
- [Do Syntax Trees Help Pre-trained Transformers Extract Information?](https://mlsanity.com/paper/2008.09084/) (2020)
- [Improving Compositional Generalization in Semantic Parsing](https://mlsanity.com/paper/2010.05647/) (2020)
- [Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language](https://mlsanity.com/paper/2210.00482/) (2022)
- [Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale](https://mlsanity.com/paper/2203.00633/) (2022)

## Built on by (most cited first, 1 of 1)

- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)

## Abstract (arXiv)

Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is sufficiently complex, the model encodes sentences that have a common syntactic structure using a systematic attention pattern. Inspired by this observation, we propose SQ-Transformer (Structurally Quantized) that explicitly encourages systematicity in the embeddings and attention layers, even with a training set of low complexity. At the embedding level, we introduce Structure-oriented Vector Quantization (SoVQ) to cluster word embeddings into several classes of structurally equivalent entities. At the attention level, we devise the Systematic Attention Layer (SAL) and an alternative, Systematically Regularized Layer (SRL) that operate on the quantized word embeddings so that sentences of the same structure are encoded with invariant or similar attention patterns. Empirically, we show that SQ-Transformer achieves stronger compositional generalization than the vanilla Transformer on multiple low-complexity semantic parsing and machine translation datasets. In our analysis, we show that SoVQ indeed learns a syntactically clustered embedding space and SAL/SRL induces generalizable attention patterns, which lead to improved systematicity.