Name extraction for unstructured Malay text

Names are categorized as proper nouns. Identifying nouns in unstructured text is very challenging since the number is almost unlimited. Name recognition can be used for part-of-speech (POS) tagging or automatic term acquisition in natural language processing (NLP). In this paper we proposed a general approach to recognize names in Malay text. Using the proposed approach, we implement an application of free indexing for indexing names from a collection of Malay texts. Our evaluation shows that the application reach 92% precision score, 54% recall score, and F-score 68% in indexing names from news´ articles.