Training the Hidden Vector State Model from Un-annotated Corpus

Abstract

Since most knowledge about protein-protein interactions still hides in biological publications, there is an increasing focus on automatically extracting information from the vast amount of biological literature. Existing approaches can be broadly categorized as rule-based or statistically-based. Rule-based approaches require heavy manual effort. On the other hand, statistically-based approaches require large-scale, richly annotated corpora in order to reliably estimate model parameters. This is normally difficult to obtain in practical applications. We have proposed a hidden vector state (HVS) model for protein-protein interactions extraction. The HVS model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. State transitions are factored into a stack shift operation similar to those of a push-down automaton followed by the push of a new preterminal category label. In this paper, we propose a novel approach based on the k-nearest-neighbors classifier to automatically train the HVS model from un-annotated data. Experimental results show the improved performance over the baseline system with the HVS model trained from a small amount of the annotated data.