Deep Communicating Agents for Abstractive Summarization

@inproceedings{elikyilmaz2018DeepCA,
  title={Deep Communicating Agents for Abstractive Summarization},
  author={Asli Çelikyilmaz and Antoine Bosselut and Xiaodong He and Yejin Choi},
  booktitle={NAACL-HLT},
  year={2018}
}
  • Asli Çelikyilmaz, Antoine Bosselut, +1 author Yejin Choi
  • Published in NAACL-HLT 2018
  • Computer Science
  • We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. [...] Key Method 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…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 136 CITATIONS

    Improving Abstractive Text Summarization with History Aggregation

    VIEW 3 EXCERPTS
    CITES RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    Hierarchical Transformers for Multi-Document Summarization

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    An Entity-Driven Framework for Abstractive Summarization

    VIEW 6 EXCERPTS
    CITES RESULTS, BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Text Summarization with Pretrained Encoders

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 20 Highly Influenced Citations

    • Averaged 45 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES

    Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning

    VIEW 2 EXCERPTS