A hybrid approach to semi-supervised named entity recognition in health, safety and environment reports

In the last few years, text mining have become the area of interests in Natural Language Processing (NLP). They share a similar idea i.e. to extract important facts from unstructured text which later help to populate database entries. Name Entity Recognition (NER) is one of the main task needed to develop text mining systems in which it is used to identify and classify entities in the text into predefined categories such as the names of persons, organizations, locations, dates, times, quantities, monetary values, percentages, etc. This paper focuses on studying the optimum solution to perform NER. To achieve our target, Health Safety and Environment (HSE) reports available from the Universiti Teknologi PETRONAS (UTP) are chosen as the case study. The UTP's HSE reports are the investigation reports which contain the information on incidents and accidents occurred during the daily operations. Many algorithms have been reported for NER ranging from simple statistical methods to advanced Natural language Processing (NLP) methods. This paper describes the possibility to apply Link Grammar (LG) and Basilisk Algorithm in NER.