# Evaluation of Unsupervised Compositional Representations

arXiv: https://arxiv.org/abs/1806.04713 · HTML: https://mlsanity.com/paper/1806.04713/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

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

- [Unsupervised Sentence-embeddings by Manifold Approximation and Projection](https://mlsanity.com/paper/2102.03795/) (2021)
- [Compressing Sentence Representation with maximum Coding Rate Reduction](https://mlsanity.com/paper/2304.12674/) (2023)

## Abstract (arXiv)

We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks. Our results confirm that weighted vector averaging can outperform context-sensitive models in most benchmarks, but structural features encoded in RNN models can also be useful in certain classification tasks. We analyzed some of the evaluation datasets to identify the aspects of meaning they measure and the characteristics of the various models that explain their performance variance.