Open AccessUse of global context for handling noisy names in discussion texts of a homeopathy discussion forum
Author(s) -
Mukta Majumder,
Sujan Kumar Saha
Publication year - 2014
Publication title -
knowledge management and e-learning: an international journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.526
H-Index - 21
eISSN - 2309-5008
pISSN - 2073-7904
DOI - 10.34105/j.kmel.2014.06.002
Subject(s) - context (archaeology) , computer science , task (project management) , homeopathy , natural language processing , artificial intelligence , information retrieval , linguistics , history , medicine , engineering , alternative medicine , archaeology , systems engineering , pathology , philosophy
The task of identifying named entities from the discussion texts in Web forums faces the challenge of noisy names. As the names are often misspelled or abbreviated, the conventional techniques have failed to detect the noisy names properly. In this paper we propose a global context based framework for handling the noisy names. The framework is tested on a named entity recognition system designed to identify the names from the discussion texts in a homeopathy diagnosis discussion forum. The proposed global context-based framework is found to be effective in improving the accuracy of the named entity recognition system.