Feature extraction using regular expression in detecting proper noun for Malay news articles based on KNN algorithm

Abstract

Pendidikan Sultan Idris, 35900Tanjong Malim, Perak, MalaysiaPublished online: ABSTRACTThe identification of proper nouns from text aims to classify named entities according to their respective groupings, an aspect included in Named Entity Recognition (NER). Proper noun disambiguation can adversely affect morphological analysis, a vital trai availability via classification and new word assimilation. The occurrences of proper nouns can be annotated from the text resources using separate entity mapping from their fragments. research was carried out to examine the impa sequence that queried and acquired proper nouns from a collection of unannotated Malay language news articles that envisions several techniques to improve text accuracy such as pre-processing and data clustering. The results showed that the F the output tested on the unannotated news dataset were between 30% and 60%.