A morpheme is an atomic expression; it has no meaningful subparts.

For example, un- or break or -able.

Morphemes are combined to form words.


1   Study

Morphology is a branch of grammar that studies morphemes.

Morphology deals with the structure of words (alphanumeric identifiers, numbers, symbolic tokens, etc.), and the grammatical and semantical categories they convey.

Morphology is the study of language at level of organizing group of sounds into meaningful units.

1.1   Structure

Morphology consists of:

  1. Lexical morphology
  2. Inflectional morphology

# Morphological analysis

# Finite State Transducer (FST)

Finite state traducers map between one representation and another.

Sequential traducers are efficient

# Stemming & Lemmatization

The goal of stemming and lemmatization is to reduce inflection form and sometimes derivationally related forms of a word to a common base form.

Example: {am, are, is} => be Example: {car, cars, car's, cars'} => car Example: "the boy's car are different color" => the boy car be differ color

## Stemming

Stemming is the process of reducing words to their stems.

  • Crude heuristic process
  • Chops off the ends of words
  • Often include the removal of derivational affixes
  • Most commonly collapses derivationally related words


  • Does morphological analysis and return the dictionary form of a word
  • Commonly only collapses the different inflectional forms of a lemma


# Natural Production

Slips of the tongue reveal that affixes can be produced separately from stems.

Example: "It's not only us who have screw looses" (for "screws loose") Example: "Words of rule formation" for "rules of word formation" Example: "easy enoughly" for "easily enough"

  • Priming tests for verifying hypotheses

A word is recognized faster if it has been seen before recently

2   Properties

Every morpheme is either free or bound. A free morpheme can function independently as a word. A bound morpheme can appear only as part of words.

Either a morpheme is lexical or a morpheme is grammatical.

3   Classification

Morphemes may be divided into two classes: word stems and affixes.