https://github.com/scionoftech/text_summarization

Text Summarization using LSTM_Attention, TextRank,PyTextRank, LexRank, Gensim and PyTeaser
https://github.com/scionoftech/text_summarization

attention gensim lexrank lstm pyteaser rnn-encoder-decoder text-summarization textrank

Last synced: 3 months ago
JSON representation

Text Summarization using LSTM_Attention, TextRank,PyTextRank, LexRank, Gensim and PyTeaser

• Host: GitHub
• URL: https://github.com/scionoftech/text_summarization
• Owner: scionoftech
• Created: 2019-12-18T19:22:32.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-12-18T19:32:24.000Z (over 5 years ago)
• Last Synced: 2024-12-27T17:23:36.217Z (5 months ago)
• Topics: attention, gensim, lexrank, lstm, pyteaser, rnn-encoder-decoder, text-summarization, textrank
• Language: Jupyter Notebook
• Size: 304 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Text Summarization

Text summarization refers to the technique of shortening long pieces of text. The intention is to create a coherent and fluent summary having only the main points outlined in the document.

Automatic text summarization is a common problem in machine learning and natural language processing (NLP).

There are broadly two different approaches that are used for text summarization:

* Extractive Summarization

* Abstractive Summarization

### Extractive Summarization

The name gives away what this approach does. We identify the important sentences or phrases from the original text and extract only those from the text. Those extracted sentences would be our summary. The below diagram illustrates extractive summarization.

![Extractive_Summarization.png](images/Extractive_Summarization.png)

### Abstractive Summarization

This is a very interesting approach. Here, we generate new sentences from the original text. This is in contrast to the extractive approach where we used only the sentences that were present. The sentences generated through abstractive summarization might not be present in the original text.

![Abstractive_Summarization.png](images/Abstractive_Summarization.png)

Text Summarization is implemented with below approches,

* LSTM,Encoder-Decodef and Attention 

* TextRank Algorithm

* PyTextRank Text Summarization

* LexRank Text Summarization

* Gensim Text Summarization

* PyTeaser Text Summarization