Generative text modeling through short run inference

Bo Pang, Erik Nijkamp, Tian Han, Ying Nian Wu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Latent variable models for text, when trained successfully, accurately model the data distribution and capture global semantic and syntactic features of sentences. The prominent approach to train such models is variational autoencoders (VAE). It is nevertheless challenging to train and often results in a trivial local optimum where the latent variable is ignored and its posterior collapses into the prior, an issue known as posterior collapse. Various techniques have been proposed to mitigate this issue. Most of them focus on improving the inference model to yield latent codes of higher quality. The present work proposes a short run dynamics for inference. It is initialized from the prior distribution of the latent variable and then runs a small number (e.g., 20) of Langevin dynamics steps guided by its posterior distribution. The major advantage of our method is that it does not require a separate inference model or assume simple geometry of the posterior distribution, thus rendering an automatic, natural and flexible inference engine. We show that the models trained with short run dynamics more accurately model the data, compared to strong language model and VAE baselines, and exhibit no sign of posterior collapse. Analyses of the latent space show that interpolation in the latent space is able to generate coherent sentences with smooth transition and demonstrate improved classification over strong baselines with latent features from unsupervised pretraining. These results together expose a well-structured latent space of our generative model.

Original languageEnglish
Title of host publicationEACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Pages1156-1165
Number of pages10
ISBN (Electronic)9781954085022
StatePublished - 2021
Event16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 - Virtual, Online
Duration: 19 Apr 202123 Apr 2021

Publication series

NameEACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021
CityVirtual, Online
Period19/04/2123/04/21

Fingerprint

Dive into the research topics of 'Generative text modeling through short run inference'. Together they form a unique fingerprint.

Cite this