Informatics Publishing Limited

N. Abinaya ¹, M. Anand Kumar ¹, K. P. Soman ¹

Affiliations
1 Centre for Excellence in Computational Engineering and Networking, Amrita Vishwa Vidyapeetham, Coimbatore - 641 112, Tamil Nadu, IN

Abstract

In this paper, we present a new approach for Named Entity Recognition (NER) in Tamil language using Random Kitchen Sink algorithm. Named Entity recognition is the process of identification of Named Entities (NEs) from the text. It involves the identifying and classifying predefined categories such as person, location, organization etc. A lot of work has been done in the field of Named Entity Recognition for English language and Indian languages using various machine learning approaches. In this work, we implement the NER system for Tamil using Random Kitchen Sink algorithm which is a statistical and supervised approach. The NER system is also implemented using Support Vector Machine (SVM) and Conditional Random Field (CRF). The overall performance of the NER system was evaluated as 86.61% for RKS, 81.62% for SVM and 87.21% for CRF. Additional results have been taken in SVM and CRF by increasing the corpus size and the performance are evaluated as 86.06% and 87.20% respectively.

Keywords

Conditional Random Field (CRF), Named Entities (NEs), Named Entity Recognition (NER), Natural Language Processing (NLP), Random Kitchen Sink (RKS), Support Vector Machine (SVM)

Full Text

   

K. Elakiya Shree ¹, N. Abinaya ²

Affiliations
1 Department of Mathematics, Sri Bharathi Arts and Science College, Pudukkottai, IN
2 Department of Mathematics, Sri Bharathi Arts and Science College, Pudukkottai., IN

Abstract

One of the applications of the Mittag-Leffler function is in modeling fractional order viscoelastic materials. Experimental investigations into the time-dependent relaxation behavior of viscoelastic materials are characterized by a very fast decrease of the stress at the beginning of the relaxation process and an extremely slow decay for large times. It can even take a long time before a constant asymptotic value is reached. Therefore, a lot of Maxwell elements are required to describe relaxation behavior with sufficient accuracy. This ends in a difficult optimization problem in order to identify a large number of material parameters. On the other hand, over the years, the concept of fractional derivatives has been introduced to the theory of viscoelasticity. Among these models, the fractional Zener model was found to be very effective to predict the dynamic nature of rubber-like materials with only a small number of material parameters. The solution of the corresponding constitutive equation leads to a relaxation function of the Mittag-Leffler type. It is defined by the power series with negative arguments. This function represents all essential properties of the relaxation process under the influence of an arbitrary and continuous signal with a jump at the origin.

Keywords

Classcal Gamma Function, Generalized k-MittagLeffler Function, Generalized Two Parameter Pochhammer Symbol, Generalized Two Parameter Gamma Function.

Full Text