Papers › Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

27 Feb 2017ICML 2017 8arXiv:1702.08139archive 2025-07-28

Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov, Taylor Berg-Kirkpatrick

Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result is so far poorly understood, but has been attributed to the propensity of LSTM decoders to ignore conditioning information from the encoder. In this paper, we experiment with a new type of decoder for VAE: a dilated CNN. By changing the decoder's dilation architecture, we control the effective context from previously generated words. In experiments, we find that there is a trade off between the contextual capacity of the decoder and the amount of encoding information used. We show that with the right decoder, VAE can outperform LSTM language models. We demonstrate perplexity gains on two datasets, representing the first positive experimental result on the use VAE for generative modeling of text. Further, we conduct an in-depth investigation of the use of VAE (with our new decoding architecture) for semi-supervised and unsupervised labeling tasks, demonstrating gains over several strong baselines.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

harvardnlp/sa-vae mentioned on GitHubpytorch report
kefirski/contiguous-succotash mentioned on GitHubpytorch report
ryokamoi/dcnn_textvae mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Generation Yahoo Questions CNN-VAE KL 10.0 #3 of 3 Archive leaderboard report
Text Generation Yahoo Questions CNN-VAE NLL 332.1 #3 of 3 Archive leaderboard report
Text Generation Yahoo Questions CNN-VAE Perplexity 63.9 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections