SideNet - An Extractive Document Summarizer

Description

This is a demo for SideNet, a neural extractive document summarization system that builds the summary by extracting relevant sentences from the document by attending side information such as title and captions in the document.

SideNet was developed by Shashi Narayan (in collaboration with Nikos Papasarantopoulos, Mirella Lapata and Shay Cohen) at the Cohort NLP/ML research group.

We thank our funders: EU H2020 (grant agreement: 688139, SUMMA) and Huawei Technologies.

SideNet’s TensorFlow source code can be found on github.

Paper

The summarizer is described in detail in the paper that can be downloaded here.

@article{sidenet-2017,
  author={Shashi Narayan and Nikos Papasarantopoulos and Mirella Lapata and Shay B. Cohen},
  title={Neural Extractive Summarization with Side Information},
  journal={CoRR},
  volume={abs/1704.04530},
  year={2017},
  ee={http://arxiv.org/abs/1704.04530},
}

Demo

Newstype:

URL of article:




Text:



Sidenet Summary

LEAD Summary

Gold Summary

LOG