Morphological Analyser
Development of Morphological Analyser for Hindi
Ankita Agarwal
Department of Computer Science , Apaji Institute, Banasthali University, Rajasthan, India
Email: agarwal_anki_23@yahoo.com
Abstract- Morphological analysis is an important part of NLP. With the analysis we can make the task of Machine translation very easy. Morphological analyzer can be implemented effectively for the language which is rich in morphemes. Hindi is an inflected language. Due to variation in the words, it is morphologically rich language. In this paper we focus on the design of a morphological analyzer. The analyzer will take a Hindi sentence or a word as an input and will analyze it properly to generate its necessary features with its root words. The features will have categories like part of speech, gender, number, and person. The analyzer will work on corpus and rule based approach.
I. Introduction
In terms of linguistics, morphology refers to formation of words by focusing on their internal structure. Morphology is divided into two classes : inflectional morphology and derivational morphology. In inflectional morphology, when a word stem is combined with a morpheme it results in same class word as of the word stem while in derivational morphology, it results in a different class word other than that of the word stem. Examples of inflectional morphemes are गाड़ी(Noun) becomes गाड़ियॉँ(Noun) on adding ियॉ as suffix whereas in derivational morphemes कठोर(Adj) becomes कठोरता(Noun) on adding ता as suffix.
The objective of our work is to develop a tool which works on morphemes and generate a good morphological analyzer for inflectional morphemes only. In this paper we discuss the development of our morphological analyzer for hindi which works on corpus and rule based approach and we also maintain a database for exceptions. In this approach, first we check whether a given input is a sentence or a word. If a user input is a hindi sentence, it tokenizes it into words then for
Ankita Agarwal
Department of Computer Science , Apaji Institute, Banasthali University, Rajasthan, India
Email: agarwal_anki_23@yahoo.com
Abstract- Morphological analysis is an important part of NLP. With the analysis we can make the task of Machine translation very easy. Morphological analyzer can be implemented effectively for the language which is rich in morphemes. Hindi is an inflected language. Due to variation in the words, it is morphologically rich language. In this paper we focus on the design of a morphological analyzer. The analyzer will take a Hindi sentence or a word as an input and will analyze it properly to generate its necessary features with its root words. The features will have categories like part of speech, gender, number, and person. The analyzer will work on corpus and rule based approach.
I. Introduction
In terms of linguistics, morphology refers to formation of words by focusing on their internal structure. Morphology is divided into two classes : inflectional morphology and derivational morphology. In inflectional morphology, when a word stem is combined with a morpheme it results in same class word as of the word stem while in derivational morphology, it results in a different class word other than that of the word stem. Examples of inflectional morphemes are गाड़ी(Noun) becomes गाड़ियॉँ(Noun) on adding ियॉ as suffix whereas in derivational morphemes कठोर(Adj) becomes कठोरता(Noun) on adding ता as suffix.
The objective of our work is to develop a tool which works on morphemes and generate a good morphological analyzer for inflectional morphemes only. In this paper we discuss the development of our morphological analyzer for hindi which works on corpus and rule based approach and we also maintain a database for exceptions. In this approach, first we check whether a given input is a sentence or a word. If a user input is a hindi sentence, it tokenizes it into words then for
References: 1. Sachi Dave, Jignashu Parikh, and Pushpak Bhattacharyaa, Interlingua-based English-Hindi Machine Translation and Language Divergence, Machine Translation 16 (4), 2001, pp. 251-304. 2 3. D. Jurafsky and J.H. Martin, Speech and Language Processing: An Introduction to natural Language Processing, Computational Linguistics, and SpeechRecognition, Prentice Hall, 2000. 4. Minnen, G., Carroll, J., and Pearce, D., Applied Morphological Processing of English, Natural Language Engineering, 7(3), pages 207–223, 2001. 10. Bharati Akshar, Vineet Chaitanya, Rajeev Sangal. 1995.Natural Language Processing: A Paninian Perspective.