# GLOSS: Generative Latent Optimization of Sentence Representations

arXiv: https://arxiv.org/abs/1907.06385 · HTML: https://mlsanity.com/paper/1907.06385/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2019.

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

- [LOLNeRF: Learn from One Look](https://mlsanity.com/paper/2111.09996/) (2021)

## Abstract (arXiv)

We propose a method to learn unsupervised sentence representations in a non-compositional manner based on Generative Latent Optimization. Our approach does not impose any assumptions on how words are to be combined into a sentence representation. We discuss a simple Bag of Words model as well as a variant that models word positions. Both are trained to reconstruct the sentence based on a latent code and our model can be used to generate text. Experiments show large improvements over the related Paragraph Vectors. Compared to uSIF, we achieve a relative improvement of 5% when trained on the same data and our method performs competitively to Sent2vec while trained on 30 times less data.