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

By Yau-Shian Wang, Hung-yi Lee. 2018

67 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Generative Models

Citations in the corpus

SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders (2019, background): “Wang and Lee (2018) trained a Cycle-GAN model (Zhu et al., 2017) to learn a document-to-summary mapping given large datasets of un-paired documents and summaries.”
Unsupervised Sentence Compression using Denoising Auto-Encoders (2018, methodology): “Wang and Lee (2018) train a generative adversarial network to encode references into a latent space and decode them in summaries using only unmatched document-summary pairs.”
SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression (2019, background): “The only directly comparable unsupervised model is the ab-stractive ‘Pretrained Generator’ of Wang and Lee (2018).”
Improved Natural Language Generation via Loss Truncation (2020, background): “Finally, on Gigaword, we also compared against a recent generative adversarial network (GAN) model with a publicly available implementation (Wang and Lee, 2018).”