Work

Deep Recurrent Generative Decoder for Abstractive Text Summarization

Year: 2017
Type: conference-paper
Abstract: We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoderdecoder model equipped with a deep recurrent generative decoder (DRGN).Latent structure information implied in the target summaries is learned based on a recurrent latent random model for improving the summarization quality.Neural variational inference is employed to address the intractable posterior inference for the recurrent latent variables.Abstractive summaries are generated based on both the generative latent variables and the discriminative deterministic states.Extensive experiments on some benchmark datasets in different languages show that DRGN achieves improvements over the state-ofthe-art methods.
Language: English
Open Access status: hybrid
OpenAlex ID: W2962974924
FWCI: 12.87
Cites: 46
Cited by: 261
Related to: 10