Deep Communicating Agents for Abstractive Summarization
We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.
PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract
CNN/Daily Mail
New York Times Annotated Corpus
Results from the Paper
Ranked #31 on
Abstractive Text Summarization
on CNN / Daily Mail
(using extra training data)
