Abstractive Document Summarization with a Graph-Based Attentional Neural Model

By Jiwei Tan, Xiaojun Wan, Jianguo Xiao. 2017

303 citations recorded by the source corpus.

Abstractive summarization is the ultimate goal of document summarization research, but previously it is less investigated due to the immaturity of text generation techniques. Recently impressive progress has been made to abstractive sentence summarization using neural models. Unfortunately, attempts on abstractive document summarization are still in a primitive stage, and the evaluation results are worse than extractive methods on benchmark datasets. In this paper, we review the difficulties of neural abstractive document summarization, and propose a novel graph-based attention mechanism in the sequence-to-sequence framework. The intuition is to address the saliency factor of summarization, which has been overlooked by prior works. Experimental results demonstrate our model is able to achieve considerable improvement over previous neural abstractive models. The data-driven neural abstractive method is also competitive with state-of-the-art extractive methods.

Subfields: Artificial Intelligence, Natural Language Processing, Summarization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Caiming Xiong
  3. Jianfeng Gao
  4. Yejin Choi
  5. Richard Socher
  6. Percy Liang
  7. Graham Neubig
  8. Luke S. Zettlemoyer

In Natural Language Processing

  1. Mohit Bansal
  2. Caiming Xiong
  3. Yejin Choi
  4. Mirella Lapata
  5. Richard Socher
  6. Jianfeng Gao
  7. Graham Neubig
  8. Luke S. Zettlemoyer

In Summarization

  1. Andreas Vlachos
  2. Hardy Hardy
  3. Bryan McCann
  4. Richard Socher
  5. Wojciech Kryscinski
  6. Yejin Choi
  7. Max Grusky
  8. Ramakanth Pasunuru

Citations in the corpus