Deep Recurrent Generative Decoder for Abstractive Text Summarization
This work addresses the problem of generating concise and coherent summaries for text data, benefiting natural language processing applications, and is incremental as it builds on existing encoder-decoder models with novel enhancements.
The authors tackled abstractive text summarization by proposing a deep recurrent generative decoder framework, which improved summarization quality by learning latent structure information and using neural variational inference, achieving state-of-the-art results on benchmark datasets in multiple languages.
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder 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-of-the-art methods.