Deep Learning for Textual Entailment Recognition

In this paper we propose a novel two-step procedure to recognize textual entailment. Firstly, we build a joint Restricted Boltzmann Machines (RBM) layer to learn the joint representation of the text-hypothesis pairs. Then the reconstruction error is calculated by comparing the original representation with reconstructed representation derived from the joint layer for each pair to recognize textual entailment. The joint RBM training data is automatically generated from a large news corpus. Experiment results show the contribution of the idea to the performance on textual entailment.