CIE uses the vector space model of retrieval (Salton & McGill, 1983). A collection of Q&A's is a vector space whose dimensions are the Q&A terms. Each Q&A is a vector of the weights assigned to its terms. A client's question is a term weight vector in the Q&A vector space. The similarity between the question vector and a Q&A vector is computed as the cosine of the angle between them, i.e., the dot product of the vectors divided by the product of their magnitudes.