Open Source Text Processing Project: PyStemmer

Python stemming library using snowball stemmers

Project Website:

Github Link:

Description

PyStemmer is a Python interface to the stemming algorithms from the Snowball project (http://snowball.tartarus.org/). A stemming algorithm (or stemmer) is a process for removing the commoner morphological and inflexional endings from words in English. Its main use is as part of a term normalisation process that is usually done when setting up Information Retrieval systems. A stemmer aims to conflate words with the same linguistic base form, in order that the resulting “stem” may be considered to represent all words with that base form.

Stemmers can be used to make searches more comprehensive. For example, stemming can ensure that a search for ‘cars’ will also find all documents that contain only ‘car’.

Snowball is a small string processing language designed for creating stemming algorithms for use in Information Retrieval. It is also the name of a project to develop a good base set of stemming algorithms.

PyStemmer uses the “libstemmer_c” C interface to the snowball algorithms, provided by the snowball project itself. This library is unmodified, but contained within the PyStemmer distribution. If you wish to upgrade PyStemmer to a more recent version of libstemmer_c (or the snowball algorithms), it should suffice to download a new copy of libstemmer_c from the snowball project, and replace the contents of the libstemmer_c subdirectory with the contents of the download.


Leave a Reply

Your email address will not be published. Required fields are marked *