Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks
This addresses the need for unpaired abstractive summarization, which is incremental as it builds on existing auto-encoder and GAN methods.
The paper tackles the problem of generating human-readable summaries from text without paired training data by using an auto-encoder with a discriminator to ensure readability, achieving promising results on English and Chinese corpora.
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, and unpaired abstractive summarization is thereby achieved. 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.