Bidirectional Long Short-Term Memory with Gated Relevance Network for Paraphrase Identification

Semantic interaction between text segments, which has been proven to be very useful for detecting the paraphrase relations, is often ignored in the study of paraphrase identification. In this paper, we adopt a neural network model for paraphrase identification, called as bidirectional Long Short-Term Memory-Gated Relevance Network (BiLSTM+GRN). According to this model, a gated relevance network is used to capture the semantic interaction between text segments, and then aggregated using a pooling layer to select the most informative interactions. Experiments on the Microsoft Research Paraphrase Corpus (MSRP) benchmark dataset show that this model achieves better performances than hand-crafted feature based approaches as well as previous neural network models.