Extractive Summarization using Deep Learning

Sukriti Verma, Vagisha Nidhi
8/15/2017
cs.CLcs.IRcs.LG

Official code: vagisha-nidhi/TextSummarizer (19 stars, last commit 2020-03-17).

Abstract

This paper proposes a text summarization approach for factual reports using a deep learning model. This approach consists of three phases: feature extraction, feature enhancement, and summary generation, which work together to assimilate core information and generate a coherent, understandable summary. We are exploring various features to improve the set of sentences selected for the summary, and are using a Restricted Boltzmann Machine to enhance and abstract those features to improve resultant accuracy without losing any important information. The sentences are scored based on those enhanced features and an extractive summary is constructed. Experimentation carried out on several articles demonstrates the effectiveness of the proposed approach. Source code available at: https://github.com/vagisha-nidhi/TextSummarizer

View on arXivView PDF

Code Implementations(1)

vagisha-nidhi/TextSummarizerOfficial100%

Automatic Text Summarization of a Single document

1910Python, Jupyter NotebookOct 21, 20166 years ago

Similar Papers

GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization

85% match1 repo22023

Content Selection in Deep Learning Models of Summarization

85% match1 repo1062018

DiffuSum: Generation Enhanced Extractive Summarization with Diffusion

84% match1 repo202023

Surveying the Landscape of Text Summarization with Deep Learning: A Comprehensive Review

83% match2023

Leveraging BERT for Extractive Text Summarization on Lectures

82% match1 repo1522019

Advancements in Natural Language Processing for Automatic Text Summarization

82% match2025

Cite this paper

@article{verma2017extractive,
  title  = {Extractive Summarization using Deep Learning},
  author = {Sukriti Verma and Vagisha Nidhi},
  year   = {2017},
  eprint = {1708.04439},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1708.04439}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1708.04439.svg)](https://codeofpaper.com/paper/1708.04439)

Discussion