foprel / text-summarizer

A simple experiment with text summarization in Python

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Smmry

A Python text summarizer inspired by Smmry and this tutorial. It contains the following functions:

  • sent_tokenizer: splits text into words per sentence
  • preprocess: removes punctuation and removes stopwords
  • tag_pos: part-of-speech tagger that selects adjectves (ADJ) and nouns(NN)
  • stem: stems words in sentences
  • text_rank: ranks sentences based on text rank algorithm
  • build_similarity_matrix: creates a cosine similarity matrix based on tfidf vectors
  • summarize: runs through all the steps above and generates a summary

About

A simple experiment with text summarization in Python


Languages

Language:Python 100.0%