In human dialogue, a single query may elicit numerous appropriate responses. The Transformer-based dialogue model produces frequently occurring sentences in the corpus since it is a one-to-one mapping function. CVAE is a technique for reducing generic replies. In this paper, we create a new dialogue model (CVAE-T) based on the Transformer with CVAE structure. We use a pre-trained MLM model to rewrite some key n-grams in responses to obtain a series of negative examples, and introduce a regularization term during training to explicitly guide the latent variable in learning the semantic differences between each pair of positive and negative examples. Experiments suggest that the method we design is capable of producing more informative replies.