[R-pkgs] release of version 0.2 of the textrank package
jwijffels at bnosac.be
Tue Dec 19 22:20:18 CET 2017
Hello R users,
I'm pleased to announce the release of version 0.2 of the textrank package
on CRAN: https://CRAN.R-project.org/package=textrank
*The package is a natural language processing package which allows one to
summarize text by finding*
*- relevant sentences*
*- relevant keywords*
This is done by constructing a sentence network which finds how sentences
are related to one another (word overlap). On that network Google Pagerank
is used in order to find relevant sentences.
In a similar way 'textrank' can also be used to extract keywords. How? A
word network is constructed by looking if words are following one another.
On top of that network the 'Pagerank' algorithm is applied to extract
relevant words. Relevant words which are following one another are next
pasted together to get keywords.
The package has a vignette at
and it also plays nicely with the udpipe package
https://CRAN.R-project.org/package=udpipe which is good for parts-of-speech
tagging, lemmatisation, dependency parsing and general NLP processing.
all the best,
[[alternative HTML version deleted]]
More information about the R-packages