Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks

Yau-Shian Wang, Hung-Yi Lee

Abstract:

Auto-encoders compress input data into a latent-space representation and reconstruct the original data from the representation. This latent representation is not easily interpreted by humans. In this paper, we propose training an auto-encoder that encodes input text into human-readable sentences. The auto-encoder is composed of a generator and a reconstructor. The generator encodes the input text into a shorter word sequence, and the reconstructor recovers the generator input from the generator output.
To make the generator output human-readable, a discriminator restricts the output of the generator to resemble human-written sentences. By taking the generator output as the summary of the input text, abstractive summarization is achieved without document-summary pairs as training data. Promising results are shown on both English and Chinese corpora.

Keywords: unsupervised learning, text summarization, adversarial training

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1810.02851/code)