Papers › Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder

Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder

14 Sep 2018arXiv:1809.05233archive 2025-07-28

Raphael Schumann

In this work we present an unsupervised approach to summarize sentences in abstractive way using Variational Autoencoder (VAE). VAE are known to learn a semantically rich latent variable, representing high dimensional input. VAEs are trained by learning to reconstruct the input from the probabilistic latent variable. Explicitly providing the information about output length during training influences the VAE to not encode this information and thus can be manipulated during inference. Instructing the decoder to produce a shorter output sequence leads to expressing the input sentence with fewer words. We show on different summarization data sets, that these shorter sentences can not beat a simple baseline but yield higher ROUGE scores than trying to reconstruct the whole sentence.

PaperPDFCode

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

Code

raphael-sch/SumVAE mentioned on GitHubtf 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

DecoderSentenceSentence SummarizationUnsupervised Sentence Summarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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