Question

I am trying to implement porter stemming algorithm, but i am having difficualties understanding this point

Step 1c

(*v*) Y -> I                    happy        ->  happi
                                sky          ->  sky

Isn’t that the the opposite of what we want to do , why does the algorithim convert the Y into I.

for the complete algorithm here http://tartarus.org/~martin/PorterStemmer/def.txt

Thanks

Answer 1

The Porter stemmer and other stemming algorithms don’t always return words; they return word stems. The goal is that related words should have the same stem. As long as “happiness”, “happy”, and “happily” all reduce to the same stem, then your stemmer is doing its job, even if the stem isn’t a real word.