Multi-way Relation Classification: Application to Protein-Protein Interactions

We address the problem of multi-way relation classification, applied to identification of the interactions between proteins in bioscience text. A major impediment to such work is the acquisition of appropriately labeled training data; for our experiments we have identified a database that serves as a proxy for training data. We use two graphical models and a neural net for the classification of the interactions, achieving an accuracy of 64% for a 10-way distinction between relation types. We also provide evidence that the exploitation of the sentences surrounding a citation to a paper can yield higher accuracy than other sentences.