Browse Definitions:


Contributor(s): Matthew Haughn

Stemming is the process of reducing a word to its word stem that affixes to suffixes and prefixes or to the roots of words known as a lemma. Stemming is important in natural language understanding (NLU) and natural language processing (NLP).

Stemming is a part of linguistic studies in morphology and artificial intelligence (AI) information retrieval and extraction. Stemming and AI knowledge extract meaningful information from vast sources like big data or the Internet since additional forms of a word related to a subject may need to be searched to get the best results. Stemming is also a part of queries and Internet search engines.

Recognizing, searching and retrieving more forms of words returns more results. When a form of a word is recognized it can make it possible to return search results that otherwise might have been missed. That additional information retrieved is why stemming is integral to search queries and information retrieval.

When a new word is found, it can present new research opportunities. Often, the best results can be attained by using the basic morphological form of the word: the lemma. To find the lemma, stemming is performed by an individual or an algorithm, which may be used by an AI system. Stemming uses a number of approaches to reduce a word to its base from whatever inflected form is encountered.

It can be simple to develop a stemming algorithm. Some simple algorithms will simply strip recognized prefixes and suffixes. However, these simple algorithms are prone to error. For example, an error can reduce words like laziness to lazi  instead of lazy. Such algorithms may also have difficulty with terms whose inflectional forms don't perfectly mirror the lemma such as with saw and see.

Examples of stemming algorithms include:

Lookups in tables of inflected forms of words. This approach requires all inflected forms be listed.

Suffix strippi . Algorithms recognize known suffixes on inflected words and remove them.

Lemmatization. This algorithm collects all inflected forms of a word in order to break them down to their root dictionary form or lemma. Words are broken down into a part of speech (the categories of word types) by way of the rules of grammar.

Stochastic models. This algorithm earns from tables of inflected forms of words. By understanding suffixes, and the rules by which they are applied, an algorithm can stem new words.

This was last updated in January 2018

Continue Reading About stemming

Start the conversation

Send me notifications when other members comment.

By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy

Please create a username to comment.


File Extensions and File Formats

Powered by:


  • risk map (risk heat map)

    A risk map, also known as a risk heat map, is a data visualization tool for communicating specific risks an organization faces.

  • internal audit (IA)

    An internal audit (IA) is an organizational initiative to monitor and analyze its own business operations in order to determine ...

  • pure risk (absolute risk)

    Pure risk, also called absolute risk, is a category of threat that is beyond human control and has only one possible outcome if ...


  • FIDO (Fast Identity Online)

    FIDO (Fast ID Online) is a set of technology-agnostic security specifications for strong authentication. FIDO is developed by the...

  • cryptanalysis

    Cryptanalysis is the study of ciphertext, ciphers and cryptosystems with the aim of understanding how they work and finding and ...

  • Trojan horse (computing)

    In computing, a Trojan horse is a program that appears harmless, but is, in fact, malicious.



  • business continuity and disaster recovery (BCDR)

    Business continuity and disaster recovery (BCDR) are closely related practices that describe an organization's preparation for ...

  • business continuity plan (BCP)

    A business continuity plan (BCP) is a document that consists of the critical information an organization needs to continue ...

  • call tree

    A call tree -- sometimes referred to as a phone tree -- is a telecommunications chain for notifying specific individuals of an ...


  • cloud SLA (cloud service-level agreement)

    A cloud SLA (cloud service-level agreement) is an agreement between a cloud service provider and a customer that ensures a ...

  • wear leveling

    Wear leveling is a process that is designed to extend the life of solid-state storage devices.

  • storage area network (SAN)

    A storage area network (SAN) is a dedicated high-speed network or subnetwork that interconnects and presents shared pools of ...


  • hybrid hard disk drive (HDD)

    A hybrid hard disk drive is an electromechanical spinning hard disk that contains some amount of NAND Flash memory.