Skip to content

andrewquirk/extractive-news-summarization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CS221 (Artificial Inteligence) Final Project

In our digital age, we are constantly bombarded with a seemingly infinite amount of information through sources such as social media, news articles, and instant messaging. Many times, the amount of diverse information (combined with increasingly shorter human attention spans) can lead to an apathy towards reading large amounts of text. This feeling is so common, that it has lead to the creation of the colloquial expression 'tl;dr' (too long didn't read) which refers to short, 3-5 sentence summaries of long sources of information. For our project, we created an algorithm that will generate readable, and useful, 'tl;dr' summary of a news article, automatically, given the article's original text.

See the final paper: cut-chase-extractive.pdf

Final score: 9.7/10

Class average: 9.01/10

About

Fall Quarter 2017, CS221 project: an extractive machine summarization model that inputs news articles and outputs useful summaries.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages