Improving on the Smoothing Technique for Obtaining Emission Probabilities in Hidden Markov Models

Hidden Markov Models (HMMs) have been shown to achieve good performance when applied to information extraction tasks. This paper describes the training aspect of exploring HMMs for the task of metadata extraction from tagged bibliographic references. The main contribution of this work is the improvement of the technique proposed by earlier researchers for smoothing emission probabilities in order to avoid the occurrence of zero values. The results show the effectiveness of the proposed method.