Kumar Nagaraj

Learn More
We present a statistical approach to Part-of-Speech(POS) tagger and chunker for Hindi language. Our system employs Maximum Entropy Markov Model (MEMM), trains from annotated Hindi corpus and assigns tags(POS tags and chunk labels) to previously unseen text. This model uses multiple features simultaneously to predict the tag for a word. The feature set is(More)
Part Of Speech (POS) tagging is the most important pre-processing step in almost all Natural Language Processing (NLP) applications. It is defined as the process of classifying each word in a text with its appropriate part of speech. In this paper, the probabilistic classifier technique of Maximum Entropy model is experimented for the tagging of Kannada(More)
In this paper we present a statistical partof-speech(POS) tagger for a morphologically rich language: Hindi. To the best of our knowledge, our tagger achieves the highest reported tagging accuracy for Hindi. Our tagger employs the maximum entropy Markov model with a rich set of features capturing the lexical and morphological characteristics of the(More)
During treatment planning it is important to recognize different gingival biotypes and forms, because they can affect the esthetic outcome of the treatment. This review provides an insight into the different gingival biotypes, their response to inflammation and trauma; significance in different prosthodontic modalities like esthetic rehabilitation and(More)
Post and core therapy is regarded as the treatment of choice for restoring severely damaged endodontically treated teeth. Critical control of endodontic materials in the coronal third of the canal and pulp chamber is essential in order to maintain its colour and translucency. In addition to this, the duplication of the optical characteristics of an intact(More)
POS tagger is the process of assigning a correct tag to each word of the sentence. We attempted to improve the accuracy of existing Punjabi POS tagger. This POS tagger lacks in resolving the ambiguity of a no of words as it uses only hand written Rules. A Bi-gram Model has been used to solve the part of speech tagging problem. An annotated corpus was used(More)
Provision for high standard of oral health care is a fundamental requirement for any individual and dentists constantly strive to provide optimal treatment to their patients. However, when it comes to treating subjects with infectious diseases particularly those attached with social stigma like HIV/AIDS, there remains doubts and hesitations. This may lead(More)
Dynamic bandwidth allocation for upstream transmission in EPONs has gathered significant attention. Maximizing utilization is inversely related to dynamic bandwidth allocation. We propose an auctioning mechanism for bandwidth allocation with a view to dissolution of the paradox between efficiency (utilization) and dynamism. While conventional bandwidth(More)
The success of the dental restorations largely depends on its esthetics, although various literature reviews recommend that anterior teeth midline be placed coinciding the facial midline, the amount of acceptable deviation between facial and dental midline has not been fully investigated. To observe the acceptable deviation between the dental and facial(More)