A great property of RNN models, when compared to many other models, is that they can deal with sequences of various lengths. Taking advantage of this, and the fact that they can generalize to sequences not seen before, we can create a way to measure how similar sequences of inputs are to each other. In this recipe, we will train a Siamese similarity RNN to measure the similarity between addresses for record matching.
Training a Siamese similarity measure
Getting ready
In this recipe, we will build a bidirectional RNN model that feeds into a fully connected layer that outputs a fixed-length numerical vector. We create a bidirectional RNN layer for both input addresses and feed the outputs into a fully connected layer that outputs...
