A Comprehensive information extraction module for reducing call handling time in a contact centre

Abstract

Information extraction plays an important role in text related research and application areas such as text mining and dialogue systems. Information extraction can be done using key word extraction and measuring the semantic similarity between texts. These concepts are applied to address a key issue in the telecommunication contact centre domain where the customer dissatisfaction is increasing due to higher call handling time. The proposed method is a combined with a key word based approach and a semantic similarity based approach with the use of semantic nets. The semantic similarity of two sentences is calculated using word similarity and the word order. Experiments on two sets of sentence pairs illustrates that proposed method provides a similar measure which is significantly correlated to human intuition. The overall accuracy of the information extraction module is approximately 70% based on the evaluation results.