# StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure

arXiv: https://arxiv.org/abs/2305.05588 · HTML: https://mlsanity.com/paper/2305.05588/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 62 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 30 of 33)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [Hierarchical Transformers Are More Efficient Language Models](https://mlsanity.com/paper/2110.13711/) (2021)
- [Compound Probabilistic Context-Free Grammars for Grammar Induction](https://mlsanity.com/paper/1906.10225/) (2019)
- [Efficient Transformers with Dynamic Token Pooling](https://mlsanity.com/paper/2211.09761/) (2022)
- [Tree Transformer: Integrating Tree Structures into Self-Attention](https://mlsanity.com/paper/1909.06639/) (2019)
- [Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders](https://mlsanity.com/paper/1904.02142/) (2019)
- [Learning to Compose Task-Specific Tree Structures](https://mlsanity.com/paper/1707.02786/) (2017)
- [Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction](https://mlsanity.com/paper/2002.00737/) (2020)
- [Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale](https://mlsanity.com/paper/2203.00633/) (2022)
- [Characterizing Intrinsic Compositionality in Transformers with Tree Projections](https://mlsanity.com/paper/2211.01288/) (2022)
- [Straight to the Tree: Constituency Parsing with Neural Syntactic Distance](https://mlsanity.com/paper/1806.04168/) (2018)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models](https://mlsanity.com/paper/2007.01179/) (2020)

## Built on by (most cited first, 2 of 2)

- [Hierarchical Indexing for Retrieval-Augmented Opinion Summarization](https://mlsanity.com/paper/2403.00435/) (2024)
- [TRA: Better Length Generalisation with Threshold Relative Attention](https://mlsanity.com/paper/2503.23174/) (2025)

## Abstract (arXiv)

This work presents StrAE: a Structured Autoencoder framework that through strict adherence to explicit structure, and use of a novel contrastive objective over tree-structured representations, enables effective learning of multi-level representations. Through comparison over different forms of structure, we verify that our results are directly attributable to the informativeness of the structure provided as input, and show that this is not the case for existing tree models. We then further extend StrAE to allow the model to define its own compositions using a simple localised-merge algorithm. This variant, called Self-StrAE, outperforms baselines that don't involve explicit hierarchical compositions, and is comparable to models given informative structure (e.g. constituency parses). Our experiments are conducted in a data-constrained (circa 10M tokens) setting to help tease apart the contribution of the inductive bias to effective learning. However, we find that this framework can be robust to scale, and when extended to a much larger dataset (circa 100M tokens), our 430 parameter model performs comparably to a 6-layer RoBERTa many orders of magnitude larger in size. Our findings support the utility of incorporating explicit composition as an inductive bias for effective representation learning.