SCIR-QA at SemEval-2017 Task 3: CNN Model Based on Similar and Dissimilar Information between Keywords for Question Similarity

We describe a method of calculating the similarity between questions in community QA. Questions in cQA are usually very long and there are a lot of useless information about calculating the similarity between questions. Therefore, we implement a CNN model based on similar and dissimilar information on questions keywords. We extract the keywords of questions, and then model the similar and dissimilar information between the keywords, and use the CNN model to calculate the similarity.