Amortized Mixture Prior for Variational Sequence Generation

Jen Tzung Chien, Chih Jung Tsai

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


Variational autoencoder (VAE) is a popular latent variable model for data generation. However, in natural language applications, VAE suffers from the posterior collapse in optimization procedure where the model posterior likely collapses to a standard Gaussian prior which disregards latent semantics from sequence data. The recurrent decoder accordingly generates du-plicate or noninformative sequence data. To tackle this issue, this paper adopts the Gaussian mixture prior for latent variable, and simultaneously fulfills the amortized regularization in encoder and skip connection in decoder. The noise robust prior, learned from the amortized encoder, becomes semantically meaningful. The prediction of sequence samples, due to skip connection, becomes contextually precise at each time. The amortized mixture prior (AMP) is then formulated in construction of variational recurrent autoencoder (VRAE) for sequence generation. Experiments on different tasks show that AMP-VRAE can avoid the posterior collapse, learn the meaningful latent features and improve the inference and generation for semantic representation.

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728169262
StatePublished - Jul 2020
Event2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
CountryUnited Kingdom
CityVirtual, Glasgow


  • language model
  • recurrent neural network
  • Sequence generation
  • variational autoencoder

Fingerprint Dive into the research topics of 'Amortized Mixture Prior for Variational Sequence Generation'. Together they form a unique fingerprint.

Cite this