Context encoder for analogies on strings

We propose a model based on context encoder to solve formal analogies on strings likeaaabbbccc : aaaabbbbcccc :: abc : x )x = aabbcc or ubid : tubid :: ofjid : x) x = tofjid. As a context encodermodel, it consists of a generator and a discriminator. The generator attempts at generating the result of an analogical equation, whilethe discriminator attempts at discriminatingsolutions coming out of the generator againstthe real solution of the analogical equation.We conduct experiments on publicly availabledata sets to compare the performance of ourmodel with a previously published method designed for the same task. Our results showslight increases in accuracy, in comparison toa fully connected neural network architecture.