Language as a Latent Variable: Discrete Generative Models for Sentence Compression

Explore this paper's citation graph

Summary

This work forms a variational auto-encoder for inference in a deep generative model of text in which the latent representation of a document is itself drawn from a discrete language model distribution and shows that generative formulations of both abstractive and extractive compression yield state-of-the-art results when trained on a large amount of supervised data.

Type
preprint
Published
2016-09-23
Cited by
228
References
50
Access
Open access

Keywords

Computer science, Latent variable, Generative model, Generative grammar, Latent variable model

References

Cited by

Related papers