stemming

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

Stemming is a process of reducing a word to its stem as a normalised form for the purposes of natural language processing, indexing or document retreval. For example, plurals are reduced to their singular form by deleting the trailing 's' and gerunds of verbs have theor 'ing' removed. Stemming is usually perfomed at a lexical level without any semantic knowledge, which can lead to a small proportion of inappropriate stems, for example, 'starling' might be stemmed to 'starl'.

Used in Chap. 16: page 241