Kannada Named Entity Recognition and Classification using Support Vector Machine
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2017, Vol 5, Issue 1
Abstract
Named Entity Recognition and Classification (NERC) is a process of identification of proper nouns in the text and classification of those nouns into certain predefined categories like person name, location, organization, date, time etc. Kannada NERC is an essential and challenging work which aims at developing a novel model based on Support Vector Machine. In this paper, tf-idf and POS features are used, which are extracted from a training corpus created manually. Furthermore, the model is trained and tested with different kernels: polynomial, rbf, sigmoid and linear kernels. The details of implementation and performance evaluation are discussed. The experiments are conducted on a training corpus of size 1, 51,440 tokens and test corpus of 7,000, 11,000, 15,000, 20,000, 30,000, 40,000 and 50,000 tokens. It is observed that the model works with an average precision, recall and F1-measure of 87%, 88% and 87.5% respectively for a linear kernel SVM on the test corpus of 7,000 tokens.
Authors and Affiliations
S Amarappa, S V Sathyanarayana
Keywords
Related Articles
- EP ID EP277053
- DOI 10.14738/tmlai.51.2549
- Views 75
- Downloads 0
Semantic Web Service Discovery Framework using Multi-Agents System and NLP Techniques
As a consequently increase amount of web services available on the web, automatic discovery presents a great challenge, in order to satisfy this requirement, semantic discovery approaches based on ontologies have been de...
Harmonic Rule for Measuring the Facial Similarities among Relatives
The harmonic rule is a strategy used to measure the harmonic distance between any pair of images. The images have been trained and tested on individual pair of facial images respectively. The facial images have been trai...
Serious Games for the Development of Lea
With the advent of interactive media, learning by playing is taking a variety of forms. Serious game, this term may seem contradictory, in reality it reflexes a very current reality, it rests on the video culture playful...
Comparative Study of Exact Continuous Orthogonal Moments Applications : Local Feature Extraction and Data Compression
This paper present an improved reconstruction algorithm of the multigray level images based on overlapping block method using exact continuous moments computation: Legendre , Zernike, PseudoZernike and Gegenbauer moments...
Counterterrorism: Privately Clustering A Radical Social Network Data
The tradeoff between the needed or essential gathering and analysis of personal data and the privacy rights of individuals is now an important requirement under any counterterrorism program. The most famous and controver...