Associative Context Classification for Natural Language Processing of Resource poor Languages

Abstract

In this thesis, we propose a generic associative classification approach called associative context classification which we have developed using our proposed context based list concept that groups items of some specific context and other proposed parameters and concepts. newlineIn our research, we have demonstrated the application of this proposed approach in developing solutions to a few representative Natural Language Processing (NLP) tasks. newlineWe have focused on developing semi-supervised methods using small sized annotated data. Our methods perform well even with less amount of training data without using domain knowledge explicitly and hence, are especially suitable for resource-poor languages which lack domain resources. newlineOur proposed approach is based on associative classification and on the one sense per collocation hypothesis which states that the sense of a word in a document is effectively determined by its context.Hence, our proposed approach can be applied for NLP tasks which depend on collocation property. newlineWe have validated the utility of our proposed approach for NLP tasks of resource-poor languages by successfully applying it for developing generic methods for Part-of-Speech (POS) tagging and Word Sense Disambiguation (WSD) tasks. newlinePOS tagging is a NLP classification task that assigns a POS tag or other lexical class marker to an item or to each item in the sentence and WSD is a classification task which involves determining the correct meaning of each word in a sentence or phrase based on the neighboring context items. newlineWe also present ensemble methods with supervised SVMTool POS tagger and CRF based POS tagger using a Decision Tree approach for POS tagging and an ensemble method with SVM classifier for WSD. newlineWe present our experimental results on resource-rich English, resource-moderate Hindi and resource-poor Bengali, Marathi, Tamil, Telugu and Urdu language datasets for POS tagging and on English, Hindi and Marathi language datasets for WSD experiments newline