Deep Communicating Agents for Abstractive Summarization
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:MHHBUCOPrecord.jsonopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning
A reinforcement learning framework for radiology report generation introduces a control parameter for precision-recall trade-off plus clinical rewards and group-relative training, claiming better NLG and clinical effi...
-
Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning
Reinforcement learning with a tunable control parameter and clinical reward enables precision-recall controllable radiology report generation that outperforms prior methods on MIMIC-CXR.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.