Named Entity Recognition in Natural languages using Hidden Markov Mode

Named Entity Recognition (NER) aims to detect and categorize named entities in a document into certain predefined named entities classes such as Name of Person, Location, Organization, River, Location, Expressions of times, Quantities, Monetary value, Percentages, etc. In the nomenclature of computational linguistics tasks, Named Entity Recognition lies in the domain of "information extraction", which detect definite kinds of information from documents as opposed to the more general task of "document management" which seeks to extract all of the information found in a document Named Entity Recognition in Indian Languages is a very problematical task. Since, In English and in Other European Languages, the method of Capitalization makes it easy to identify the Proper Nouns in a document, which is not so in case of Indian Languages. Moreover, Indian languages are free order, and highly inflectional and morphologically rich in nature. I have performed NER using HMM in following Natural Languages: Hindi, Bengali, Telugu, Urdu, Marathi, Punjabi, English and French. I have also dealt with problem of Unknown words in Named Entity Recognition using Transliteration.