Morphological Analysis

1148 Words5 Pages

Abstract: Morphological Analyzer is an important part in Natural Language Processing. Morphological Analyzer always returns the morpheme and its associated grammatical structure. This paper describes about the different techniques in morphological analyzer and different implementations of morphological analyzer in Malayalam.
1. INTRODUCTION
Morphological analysis is the study of the structure and formation of words. The basic unit is called as morpheme. Morpheme is smallest units which have meaning. There are two classes for morphemes which is stem and other is affixes. Stem is always the meaning bearing word and affixes are the pieces which Morphological structure is just one way of grouping languages.
Usually there are three classification …show more content…

• The constraints can refer to the lexical context, to the surface context, or to both contexts at the same time.
• Lexical lookup and morphological analysis are performed in tandem
2.3.Finite State Transducers
FST is an advanced version of FSA. FST is used to represent the lexicon computationally . It can be done by accepting the principle of two level morphology .
The two level morphology represents a word as a correspondence between lexical level and surface level . An FST is represented as a two tape automaton. We can combine lexicon, orthographic rules and spelling variations in the FST to build a morphological analyzer .Tamil morphological analyser utilizes this principle side by side with paradigm.
2.4 Stemmer
Stemmer is used to stripping of affixes. It uses a set of rules containing list of stems and replacement rules.
E.g: writing -> write + ing
For a stemmer programme we have to specify all possible affixes with replacement rules.
E.g. ational -> ate relational -> …show more content…

In highly agglutinative languages such as Malayalam, a word is formed by adding suffixes to the root or stem. Absolutely no prefixes and circumfixes are there in Malayalam. But morphologically highly complex words exist in such languages, which are formed by continuously adding suffixes to the stem. Suffix Stripping method make use of this property of the language, i.e., having complex suffixes attached to the stem. Once the suffix is identified, the stem of the whole word can be obtained by removing that suffix and applying proper sandhi

Open Document