What is stemming?
Stemming is reducing a word to the simplest form. For example- running will be simplified to run.
While performing a search, the search engine also tries to find not only an exact match to the typed search query but also other variations of the search query.
For instance, when someone tries to search for running, the search engine tries to find different forms of the term “run”, instead of trying to only match “running”.
How Stemming works-
Most stemmers work by trying to find the root word of a given search query.
There are different algorithms for stemming, but the most common in English is the Porter stemmer written by Martin Porter. For example, the Porter stemmer reduces apple and apples down to apply, and it stems berry and berries to berri.
The most popular open-source stemmer is snowball http://snowball.tartarus.org/
- Porter Stemmer- You can experience the porter stemmer from here. http://9ol.es/porter_js_demo.html
- Snowball Stemmer –Snowball stemmer can be experienced here. http://textanalysisonline.com/nltk-snowball-stemmerHere is also an example of the snowball stemmer is action.
Expertrec comes with a default stemming algorithm. You can create your own search from here.