Simple similarity-based question answering strategies for biomedical text

We introduce an approach to question answering in the biomedical domain that utilises similarity matching of question/answer pairs in a document, or a set of background documents, to select the best answer to a multiple-choice question. We explored a range of possible similarity matching methods, ranging from simple word overlap, to dependency graph matching, to feature-based vector similarity models that incorporate lexical, syntactic and/or semantic features. We found that while these methods performed reasonably well on a small training set, they did not generalise well to the final test data.