Skip to content

Unsupervised text summarization techniques for wikipedia articles in tamil.

Notifications You must be signed in to change notification settings

aalavandhan/tamil-text-summarization

Repository files navigation

Text Summarization in Tamil

Method 1 - Sentence Scoring

Refrence : Section 2.1

python sentence-scoring.py [ PATH TO FILE ] [ N-SUMMARY-SENTENCES ] [ FILE HEADING ]
# (eg) python sentence-clustering.py test/data/article-4 'மதுரை மீனாட்சி அம்மனுக்கு பட்டாபிஷேகம்' 3

Method 2 - Sentence Weighing

Refrence : Section 2.2

python sentence-weighing.py [ PATH TO FILE ]  [ N-SUMMARY-SENTENCES ]
# (eg) python sentence-clustering.py test/data/article-4 3

Method 3 - Clustering Approach

Refrence : Section 3.3

python sentence-clustering.py [ PATH TO FILE ] [ N-GRAMS ] [ N-CLUSTERS ] [ TERM-WEIGHT-TYPE ]
# TYPE = 1 -> Bool
# TYPE = 2 -> TF
# TYPE = 3 -> IDF
# TYPE = 4 -> TF-IDF
# (eg) python sentence-clustering.py test/data/article-4 3 3 4

Loading Wiki Data

mkidr test
mkidr test/data
mkidr test/summaries
mkidr test/title
cd util

python wiki_loader.py


About

Unsupervised text summarization techniques for wikipedia articles in tamil.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages