Skip to content

There are existing methods in Natural Language Processing (NLP) which can find similarity between two longer texts (based on word co-occurence and statistics) but this project deals with shorter texts. It undertakes semantics and syntatic strucutre of a sentence.

Notifications You must be signed in to change notification settings

pritishyuvraj/ShortTextSimilarity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Semantic Similairty Determination of Short Text

Paper Implemented -> Abhay Kashyap, Lushan Han, Roberto Yus, Jennifer Sleman, Taneeya Satyapanich, Sunil Gandhi, Tim Finn, “Robust Semantic Text Similarity using LSA, Machine Learning, and Linguistic Resources”, Springer Transaction. 2016.

Final Result Graph alt text Check the project PPT: Project PPT

Correlation score between Machine Predicted score and Human score is ~78%

To Check the similarity between two small texts:

  1. python flask3.py (Switch on the server)
  2. Open the file input.php on the web-browser
  3. Enter the two sentences and click on "OK"
  4. Open the file "index.php" to view the results

TO check the overall Correlation score:

  1. python extract.py

About

There are existing methods in Natural Language Processing (NLP) which can find similarity between two longer texts (based on word co-occurence and statistics) but this project deals with shorter texts. It undertakes semantics and syntatic strucutre of a sentence.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published