Spontaneous identification of individual nick name from web
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2013, Vol 4, Issue 6
Abstract
A person is generally called by different names, it is difficult to identify a person from the web, person will be called by different names by different people for example, Michael Jackson is called as MJ and some call him ” king of pop” , so there will be not trouble-free in penetrating the names from the web . Accurate identification of name of a given person is useful in various web related tasks such as information extraction, sentiment analysis, personal name disambiguation, and relative pulling out. I recommend a method to extract nick name of a given person name from the web. Given a name, the proposed method first extracts a set of candidate nick names, there after i rank the extracted candidates according to the likelihood of a candidate being a correct nickname of the given name. I propose a system, automatically extracted lexical pattern-based approach to efficiently extract a large set of candidate nick names from snippets retrieved from a web investigate engine. I identify various grade scores to estimate candidate nick name using three approach: 1.lexical pattern frequency, 2. word co-occurrences in an anchor text graph, and 3.page counts on the web. To construct a robust nick name finding system, i incorporate the dissimilar ranking scores into a single ranking function using ranking support vector machines. I assess the planned method on three data sets: an English personal names data set and place names data set and a popular personal names data set. The projected method outperforms numerous baselines and previously proposed name alias extraction methods, achieving a statistically momentous mean reciprocal rank (MRR) of 0.67.Experiments carried out using location names and popular personal names suggest the possibility of extending the proposed method to extract nick name for different types of named entities and for different languages.
Authors and Affiliations
Prof. Ajanthaa Lakkshmanan
Keywords
Related Articles
- EP ID EP120347
- DOI -
- Views 134
- Downloads 0
Genetic Programming and Artificial Neural Networks in a Chemical Process System
The main objective in this paper is to develop a mathematical model of the glucose to gluconic acid batch fermentation process utilizing novel techniques such as Genetic Programming and Artificial Neural Networks. Downlo...
A SURVEY ON ENERGY CONSUMPTION IN WIRELESS ROVING APPLICATION
Recent days, the energy consumption of mobile and tablet devices has become most familiar problem in android operating system. Android is an open source code which is easily understandable and handle by the users to get...
Data Link Layer-Security Issues
Security issues in the data link layer are not properly explained while network security problems in other layers of OSI model are studied and addressed. In this paper, we propose a new security inter-layering structure...
Survey on Service Migration to Cloud Architecture
This paper contributes to the growing knowledge of how to migrate existing systems to cloud computing environment. An increasing number of companies are expected to migrate their systems to cloud enabled infrastructures....
AI Banking Agent
Our application is designed for the web-clients of banks. Although, banks are always looking out for powerful and user friendly applications while upgrading their website [18], our platformindependent AI application uses...