Normalized Alignment of Dependency Trees for Detecting Textual Entailment

In this paper, we investigate the usefulness of normalized alignment of dependency trees for entailment prediction. Overall, our approach yields an accuracy of 60% on the RTE2 test set, which is a significant improvement over the baseline. Results vary substantially across the different subsets, with a peak performance on the summarization data. We conclude that normalized alignment is useful for detecting textual entailment, but a robust approach will probably need to include additional sources of information.