GLOSS: Generative Latent Optimization of Sentence Representations

07/15/2019
by   Sidak Pal Singh, et al.
0

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 method performs competitively to Sent2vec while trained on 30 times less data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset