Asli Celikyilmaz, Antoine Bosselut, Xiaodong He, Yejin Choi
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Text Summarization | CNN / Daily Mail | ROUGE-1 | 41.69 | DCA |
| Text Summarization | CNN / Daily Mail | ROUGE-2 | 19.47 | DCA |
| Text Summarization | CNN / Daily Mail | ROUGE-L | 37.92 | DCA |
| Abstractive Text Summarization | CNN / Daily Mail | ROUGE-1 | 41.69 | DCA |
| Abstractive Text Summarization | CNN / Daily Mail | ROUGE-2 | 19.47 | DCA |
| Abstractive Text Summarization | CNN / Daily Mail | ROUGE-L | 37.92 | DCA |