Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder
share
In this work we present a unsupervised approach to summarize sentences in an abstractive way using Variational Autoencoder (VAE). VAE are known to learn a semantically rich latent variable, representing the a 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.
READ FULL TEXT