An improved method for extracting acronym-definition pairs from biomedical Literature

This paper deals with the problem of extracting acronym-definition pairs from biomedical text. We propose an improved Text mining system based on pattern matching method and space reduction heuristics which increases both recall and precision. Three metrics were used for evaluating the system - recall (measure of how much relevant data the system has extracted from text), precision (measure of how much data returned by the system is actually correct) and f-factor (combined value of recall and precision). Experimental results achieved 98.68% recall and 98.68% precision.