Skip to content
This repository was archived by the owner on Oct 22, 2022. It is now read-only.

pvij/expand-rank-with-string-subsequence-kernel

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

ExpandRank Algo Implementation with String Subsequence Kernel

Table of Contents

Aim

To extract keywords from a document

Idea

The idea here is to construct a knowledge context, that is to select k documents nearest to the the document from which key phrases have to be extracted. The graph based ranking algorithm is then applied on the expanded document set to make use of both the local information in the specified document and the global information in the neighbour documents.The ExpandRank paper uses cosine similarity for finding out the k nearest documents to the document from which keywords have to be extracted. This implementation uses String Subsequence Kernel for measuring the similarity between two documents.

Data

The experiment was performed for 1000 documents from Hulth2003 dataset (Training), which is a collection of abstracts from different papers each with a set of associated human labelled keywords. For each document, a score was calculated and then the average of the score over those 1000 documents was used to see how well the algorithm works. The dataset can be found here.

Description of the experiment

A detailed description of the experiment can be found here.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages