• Publications
  • Influence
A sequence labeling approach to morphological analyzer for Tamil language
A novel approach is proposed to solve the morphological analyzer problem using machine learning methodology based on sequence labeling and training by kernel methods that captures the non linear relationships of the Morphological features from training data samples in a better and simpler way. Expand
Security Model for TCP/IP Protocol Suite
Some of the security flaws of IPv6 are identified and a new architecture for TCP/IP protocol suite is presented, which includes a layer called security layer, which guarantees security to Application layer using a protocol Application layer security protocol (ALSP). Expand
Morphological Analyzer for Agglutinative Languages Using Machine Learning Approaches
This new and state of the art machine learning approach based on sequence labeling and training by kernel methods captures the non-linear relationships in the different aspect of morphological features of natural languages in a better and simpler way. Expand
Language learning for visual and auditory learners using scratch toolkit
This paper has developed a scratch based tool for learning simple sentence construction of secondary language through primary language and claims that this visual learning will help people remember easily than to read as texts in books and the auditory learning helps in proper pronunciation of words rather than expecting someone's help. Expand
A deep learning approach for Malayalam morphological analysis at character level
A deep learning approach is proposed for learning the rules for identifying the morphemes automatically and segmenting them from the original word, to identify the grammatical structure of the word. Expand
Morphological Generator for Tamil
Unsupervised word embedding based polarity detection for tamil tweets
This work has used word embedding and unsupervised methodology to identify the polarity of Tamil tweets and evaluated the system using SAIL-2015 data set available for Tamil language and was able to obtain state-of-art accuracy. Expand
A Fast and Efficient Framework for Creating Parallel Corpus
A faster and efficient way of generating English to Indian languages parallel corpus with less human involvement is proposed with the help of a special type of scanner called Scansnap SV600 and Google OCR and a little linguistic knowledge. Expand
An Overview of the Shared Task on Machine Translation in Indian Languages (MTIL) – 2017
An overview of the Machine Translation in Indian Languages shared task conducted on September 7–8, 2017, is presented, which aims to examine the state-of-the-art machine translation systems when translating from English to Indian languages and to create an open-source parallel corpus for Indian languages, which is lacking. Expand